Skip to content

Benchmark

LMArena (text)

LMArena · source page ↗ · last checked Oct 9, 2026, 12:02 PM

Current leaderboard

captured Oct 9, 2026, 12:02 PM

Model	Arena Elo (text, overall)
gemini-4-argon-high	1534
claude-opus-5.5-high	1515
claude-fable-5.1-max	1510
claude-opus-5-max	1507
claude-opus-4-6-high	1503
claude-opus-5-high	1503
gemini-3.8-flash-high	1499
claude-opus-4-6	1498
mimo-v2.6-pro	1492
claude-fable-5-high	1491
claude-opus-4-7-high	1490
muse-spark-1.3-max	1490
gemini-3.7-flash-high	1486
qwen3.8-max	1483
claude-opus-4-7	1483
muse-spark-1.2 (xHigh)	1482
gemini-3.5-flash-high	1482
gemini-3.1-pro-preview	1481
gemini-3-pro	1479
gemini-3.6-flash-high	1479
muse-spark-1.1	1479
gemini-3.5-flash-medium	1477
qwen3.7-max-preview	1476
kimi-k3-max	1476
muse-spark	1474

Change history

Benchmark Oct 9, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +34 −34

- amazon-nova-experimental-chat-26-02-10 1449
- claude-fable-5-high 1492
- claude-fable-5.1-max 1511
- claude-opus-5-high 1502
- claude-opus-5.5-high 1512
- claude-sonnet-5-high 1443
- claude-sonnet-5.5-xhigh 1467
- deepseek-v4-pro-high-20260813 1445
- ernie-5.0-preview-1203 1442
- gemini-3.1-pro-preview 1480
- gemini-3.5-flash-medium 1478
- gemini-3.7-flash-high 1487
- gemini-3.8-flash-high 1497
- gemini-4-argon-high 1533
- glm-4.7 1436
- glm-5.3-flash 1470
- gpt-5.5-high 1471
- gpt-5.6-luna-xhigh 1431
- gpt-5.6-sol-xhigh 1456
- gpt-5.6-terra-xhigh 1446
- gpt-6-astra-max 1442
- gpt-6.1-sol-max 1446
- grok-4.1-thinking 1437
- grok-4.20-beta1 1444
- grok-4.6-high 1427
- hy3 1441
- inkling 1442
- longcat-flash-chat-2602-exp 1427
- mimo-v2.6-flash 1456
- mimo-v2.6-pro 1491
- minimax-m3 1432
- muse-spark-1.2 (xHigh) 1483
- qwen3.8-max 1482
- Step 5 Preview 1448
+ amazon-nova-experimental-chat-26-02-10 1448
+ claude-fable-5-high 1491
+ claude-fable-5.1-max 1510
+ claude-opus-5-high 1503
+ claude-opus-5.5-high 1515
+ claude-sonnet-5-high 1442
+ claude-sonnet-5.5-xhigh 1471
+ deepseek-v4-pro-high-20260813 1446
+ ernie-5.0-preview-1203 1443
+ gemini-3.1-pro-preview 1481
+ gemini-3.5-flash-medium 1477
+ gemini-3.7-flash-high 1486
+ gemini-3.8-flash-high 1499
+ gemini-4-argon-high 1534
+ glm-4.7 1435
+ glm-5.3-flash 1471
+ gpt-5.5-high 1472
+ gpt-5.6-luna-xhigh 1430
+ gpt-5.6-sol-xhigh 1457
+ gpt-5.6-terra-xhigh 1447
+ gpt-6-astra-max 1440
+ gpt-6.1-sol-max 1447
+ grok-4.1-thinking 1436
+ grok-4.20-beta1 1445
+ grok-4.6-high 1428
+ hy3 1439

Benchmark Oct 3, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +24 −24

- claude-opus-4-6-high 1504
- claude-opus-4-7 1484
- claude-opus-5-high 1503
- deepseek-v3.2 1425
- deepseek-v3.2-exp-thinking 1425
- deepseek-v4.1-flash-max 1461
- dola-seed-2.0-pro 1449
- gemini-3.5-flash-high 1481
- gemini-3.5-flash-lite 1434
- gemini-3.6-flash-high 1480
- gemini-3.8-flash-high 1496
- glm-5.3-max 1472
- glm-5v-turbo 1438
- gpt-6-astra-max 1441
- grok-3-preview-02-24 1426
- grok-4.20-multi-agent-beta-0309 1451
- hy3 1442
- mimo-v2.6-flash 1458
- mistral-large-3 1427
- muse-spark-1.1 1480
- muse-spark-1.2 (xHigh) 1484
- qwen3.5-max-preview 1471
- qwen3.7-max-preview 1475
- qwen3.8-max 1481
+ claude-opus-4-6-high 1503
+ claude-opus-4-7 1483
+ claude-opus-5-high 1502
+ claude-sonnet-5.5-xhigh 1467
+ deepseek-v4.1-flash-max 1462
+ dola-seed-2.0-pro 1448
+ gemini-3.5-flash-high 1482
+ gemini-3.5-flash-lite 1435
+ gemini-3.6-flash-high 1479
+ gemini-3.8-flash-high 1497
+ glm-5.3-max 1471
+ glm-5v-turbo 1437
+ gpt-6-astra-max 1442
+ gpt-6.1-sol-max 1446
+ grok-4.20-multi-agent-beta-0309 1450
+ hy3 1441
+ mimo-v2.6-flash 1456
+ mistral-large-3 1428
+ muse-spark-1.1 1479
+ muse-spark-1.2 (xHigh) 1483
+ qwen3.5-max-preview 1470
+ qwen3.7-max-preview 1476
+ qwen3.8-max 1482
+ Step 5 Preview 1448

Benchmark Oct 1, 2026, 6:03 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +34 −34

- claude-fable-5-high 1491
- claude-opus-4-8 1453
- claude-opus-4-8-high 1460
- claude-opus-5-high 1504
- claude-opus-5-max 1506
- claude-opus-5.5-high 1518
- deepseek-v3.2 1424
- deepseek-v4.1-flash-max 1465
- dola-seed-2.0-pro 1448
- gemini-3.5-flash-lite 1436
- gemini-3.5-flash-medium 1476
- gemini-3.6-flash-high 1478
- gemini-3.8-flash-high 1494
- glm-4.7 1435
- glm-5.1 1462
- glm-5.3-flash 1471
- glm-5v-turbo 1437
- gpt-5.6-luna-xhigh 1432
- gpt-6-astra-max 1443
- grok-4.1-thinking 1436
- grok-4.20-beta1 1445
- grok-4.20-multi-agent-beta-0309 1450
- grok-4.5 1447
- inkling 1443
- mimo-v2.5 1427
- mimo-v2.6-flash 1459
- minimax-m3 1433
- mistral-medium-2508 1424
- muse-spark-1.1 1478
- muse-spark-1.2 (xHigh) 1486
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 1444
- qwen3.7-max-preview 1476
- qwen3.7-plus 1454
- qwen3.8-max 1480
+ claude-fable-5-high 1492
+ claude-opus-4-8 1454
+ claude-opus-4-8-high 1461
+ claude-opus-5-high 1503
+ claude-opus-5-max 1507
+ claude-opus-5.5-high 1512
+ deepseek-v3.2 1425
+ deepseek-v4.1-flash-max 1461
+ dola-seed-2.0-pro 1449
+ gemini-3.5-flash-lite 1434
+ gemini-3.5-flash-medium 1478
+ gemini-3.6-flash-high 1480
+ gemini-3.8-flash-high 1496
+ gemini-4-argon-high 1533
+ glm-4.7 1436
+ glm-5.1 1461
+ glm-5.3-flash 1470
+ glm-5v-turbo 1438
+ gpt-5.6-luna-xhigh 1431
+ gpt-6-astra-max 1441
+ grok-4.1-thinking 1437
+ grok-4.20-beta1 1444
+ grok-4.20-multi-agent-beta-0309 1451
+ grok-4.5 1448
+ inkling 1442
+ mimo-v2.5 1428

Benchmark Sep 26, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +58 −58

- amazon-nova-experimental-chat-26-02-10 1448
- claude-fable-5 1493
- claude-fable-5.1-max 1508
- claude-opus-4-5-20251101 1450
- claude-opus-4-5-20251101-high-32k 1447
- claude-opus-4-6-high 1503
- claude-opus-4-7 1483
- claude-opus-4-8-high 1461
- claude-opus-5-high 1505
- claude-opus-5-max 1505
- claude-sonnet-4-5-20250929 1438
- claude-sonnet-4-5-20250929-high-32k 1434
- claude-sonnet-5-high 1442
- deepseek-v3.2 1425
- deepseek-v3.2-exp 1423
- deepseek-v4-flash-high-preview 1424
- deepseek-v4-pro-high-20260813 1444
- ernie-5.0-0110 1444
- ernie-5.0-preview-1203 1443
- gemini-3-flash 1467
- gemini-3.5-flash-high 1482
- gemini-3.6-flash-high 1476
- gemini-3.7-flash-high 1490
- gemini-3.8-flash-high 1495
- gemma-4-31b 1442
- glm-4.7 1436
- glm-5.2-max 1467
- glm-5.3-flash 1472
- glm-5.3-max 1475
- glm-5v-turbo 1436
- gpt-5.1 1423
- gpt-5.1-high 1442
- gpt-5.4 1453
- gpt-5.4-high 1470
- gpt-5.5 1466
- gpt-5.6-luna-xhigh 1430
- gpt-5.6-sol-xhigh 1455
- gpt-6-astra-max 1444
- grok-3-preview-02-24 1425
- grok-4.1-thinking 1437
- grok-4.20-beta1 1444
- grok-4.5 1450
- grok-4.6-high 1430
- hy3 1441
- inkling 1440
- kimi-k2.5-thinking 1446
- kimi-k3-max 1472
- longcat-flash-chat 1423
- longcat-flash-chat-2602-exp 1426
- mistral-medium-2508 1425
- muse-spark 1473
- muse-spark-1.1 1480
- muse-spark-1.2 (xHigh) 1489
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 1445
- qwen3.6-max-preview 1446
- qwen3.7-max-preview 1474
- qwen3.8-27b 1439
- qwen3.8-max 1481
+ amazon-nova-experimental-chat-26-02-10 1449
+ claude-fable-5-high 1491

Benchmark Sep 14, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +23 −23

- claude-fable-5 1492
- claude-fable-5.1-max 1510
- claude-opus-4-8 1452
- claude-opus-4-8-high 1462
- claude-opus-5-max 1504
- deepseek-v3.2-exp 1422
- deepseek-v4-pro-high-20260813 1443
- gemini-3.5-flash-high 1483
- gemini-3.6-flash-high 1475
- gemini-3.7-flash-high 1491
- gemini-3.8-flash-high 1494
- gemma-4-26b-a4b 1435
- glm-5.3-max 1477
- gpt-5.6-luna-xhigh 1431
- gpt-5.6-sol-xhigh 1454
- gpt-6-astra-max 1442
- grok-4.5 1451
- inkling 1439
- mimo-v2-omni 1422
- minimax-m3 1434
- muse-spark-1.1 1481
- qwen3.5-397b-a17b 1439
- qwen3.8-27b 1440
+ claude-fable-5 1493
+ claude-fable-5.1-max 1508
+ claude-opus-4-8 1453
+ claude-opus-4-8-high 1461
+ claude-opus-5-max 1505
+ deepseek-v3.2-exp 1423
+ deepseek-v4-pro-high-20260813 1444
+ gemini-3.5-flash-high 1482
+ gemini-3.6-flash-high 1476
+ gemini-3.7-flash-high 1490
+ gemini-3.8-flash-high 1495
+ gemma-4-26b-a4b 1434
+ glm-5.3-max 1475
+ gpt-5.6-luna-xhigh 1430
+ gpt-5.6-sol-xhigh 1455
+ gpt-6-astra-max 1444
+ grok-4.5 1450
+ inkling 1440
+ minimax-m3 1433
+ muse-spark-1.1 1480
+ muse-spark-1.3-max 1490
+ qwen3.5-397b-a17b 1438
+ qwen3.8-27b 1439

Benchmark Sep 12, 2026, 6:03 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +33 −33

- amazon-nova-experimental-chat-12-10 1421
- claude-fable-5 1494
- claude-fable-5.1-max 1514
- claude-opus-5-max 1505
- claude-sonnet-5-high 1443
- deepseek-r1-0528 1427
- deepseek-v3.2-exp 1423
- deepseek-v4-pro-high-20260813 1440
- ernie-5.0-preview-1203 1442
- gemini-3.5-flash-high 1484
- gemini-3.5-flash-medium 1477
- gemini-3.6-flash-high 1476
- gemini-3.8-flash-high 1495
- glm-5.1 1463
- glm-5.3-flash 1471
- glm-5.3-max 1474
- glm-5v-turbo 1437
- gpt-5.5 1467
- gpt-5.6-luna-xhigh 1430
- gpt-5.6-sol-xhigh 1455
- gpt-5.6-terra-xhigh 1447
- grok-4.5 1453
- hy3 1440
- inkling 1438
- kimi-k3-max 1476
- mimo-v2.5 1428
- minimax-m3 1435
- mistral-large-3 1428
- mistral-medium-3.5 1421
- muse-spark-1.1 1479
- qwen3.5-397b-a17b 1438
- qwen3.8-27b 1438
- qwen3.8-max 1480
+ claude-fable-5 1492
+ claude-fable-5.1-max 1510
+ claude-opus-5-max 1504
+ claude-sonnet-5-high 1442
+ deepseek-r1-0528 1428
+ deepseek-v3.2-exp 1422
+ deepseek-v4-pro-high-20260813 1443
+ ernie-5.0-preview-1203 1443
+ gemini-3.5-flash-high 1483
+ gemini-3.5-flash-medium 1476
+ gemini-3.6-flash-high 1475
+ gemini-3.8-flash-high 1494
+ glm-5.1 1462
+ glm-5.3-flash 1472
+ glm-5.3-max 1477
+ glm-5v-turbo 1436
+ gpt-5.5 1466
+ gpt-5.6-luna-xhigh 1431
+ gpt-5.6-sol-xhigh 1454
+ gpt-5.6-terra-xhigh 1446
+ gpt-6-astra-max 1442
+ grok-4.5 1451
+ grok-4.6-high 1430
+ hy3 1441
+ inkling 1439
+ kimi-k3-max 1472
+ mimo-v2.5 1427

Benchmark Sep 6, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +15 −15

- claude-opus-4-8-high 1461
- claude-opus-5-high 1504
- ernie-5.0-preview-1203 1443
- gemini-3-pro 1480
- gemini-3.5-flash-medium 1476
- gpt-5.1 1422
- gpt-5.5-high 1472
- grok-4.5 1452
- grok-4.6-high 1444
- mimo-v2.5 1427
- mimo-v2.5-pro 1466
- muse-spark 1474
- muse-spark-1.2 (xHigh) 1488
- qwen3-vl-235b-a22b-instruct 1420
- qwen3.8-27b 1437
+ claude-fable-5.1-max 1514
+ claude-opus-4-8-high 1462
+ claude-opus-5-high 1505
+ ernie-5.0-preview-1203 1442
+ gemini-3-pro 1479
+ gemini-3.5-flash-medium 1477
+ gemini-3.8-flash-high 1495
+ gpt-5.1 1423
+ gpt-5.5-high 1471
+ grok-4.5 1453
+ mimo-v2.5 1428
+ mimo-v2.5-pro 1465
+ muse-spark 1473
+ muse-spark-1.2 (xHigh) 1489
+ qwen3.8-27b 1438

Benchmark Sep 2, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +28 −28

- claude-fable-5 1495
- claude-opus-4-6 1497
- claude-sonnet-5-high 1442
- deepseek-v4-pro-high-20260813 1441
- ernie-5.0-preview-1203 1442
- gemini-3.5-flash-high 1483
- gemini-3.5-flash-lite 1437
- gemini-3.5-flash-medium 1475
- gemini-3.6-flash-high 1477
- gemini-3.7-flash-high 1490
- glm-5.3-flash 1466
- glm-5.3-max 1475
- gpt-5.1 1423
- gpt-5.5 1466
- gpt-5.5-high 1471
- gpt-5.6-luna-xhigh 1429
- gpt-5.6-sol-xhigh 1454
- grok-4.20-beta1 1445
- grok-4.5 1451
- hy3 1441
- inkling 1439
- mimo-v2-omni 1423
- mimo-v2-pro 1437
- mimo-v2.5 1428
- mimo-v2.5-pro 1465
- minimax-m3 1434
- muse-spark-1.1 1478
- qwen3.7-plus 1455
+ claude-fable-5 1494
+ claude-opus-4-6 1498
+ claude-sonnet-5-high 1443
+ deepseek-v4-pro-high-20260813 1440
+ ernie-5.0-preview-1203 1443
+ gemini-3.5-flash-high 1484
+ gemini-3.5-flash-lite 1436
+ gemini-3.5-flash-medium 1476
+ gemini-3.6-flash-high 1476
+ gemini-3.7-flash-high 1491
+ glm-5.3-flash 1471
+ glm-5.3-max 1474
+ gpt-5.1 1422
+ gpt-5.5 1467
+ gpt-5.5-high 1472
+ gpt-5.6-luna-xhigh 1430
+ gpt-5.6-sol-xhigh 1455
+ grok-4.20-beta1 1444
+ grok-4.5 1452
+ hy3 1440
+ inkling 1438
+ mimo-v2-omni 1422
+ mimo-v2-pro 1436
+ mimo-v2.5 1427
+ mimo-v2.5-pro 1466
+ minimax-m3 1435
+ muse-spark-1.1 1479
+ qwen3.7-plus 1454

Benchmark Aug 28, 2026, 6:03 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +35 −35

- amazon-nova-experimental-chat-12-10 1420
- amazon-nova-experimental-chat-26-02-10 1447
- claude-opus-5-max 1504
- claude-sonnet-4-5-20250929-high-32k 1433
- deepseek-r1-0528 1428
- deepseek-v3.2-exp-thinking 1424
- deepseek-v4-pro-high-20260813 1439
- ernie-5.0-preview-1022 1429
- gemini-2.5-pro 1457
- gemini-3-flash 1466
- gemini-3-pro 1479
- gemini-3.5-flash-lite 1436
- gemini-3.6-flash-high 1476
- glm-4.5 1429
- glm-4.7 1435
- glm-5 1445
- glm-5.1 1464
- glm-5.2-max 1465
- glm-5.3-max 1477
- gpt-5.1 1422
- gpt-5.1-high 1441
- gpt-5.6-terra-xhigh 1446
- grok-4.20-beta1 1444
- grok-4.5 1452
- kimi-k2.5-instant 1420
- kimi-k2.5-thinking 1445
- longcat-flash-chat 1422
- mimo-v2-omni 1422
- mimo-v2.5 1427
- minimax-m3 1435
- muse-spark-1.2 (xHigh) 1487
- qwen3-vl-235b-a22b-instruct 1421
- qwen3.7-plus 1456
- qwen3.8-27b 1441
- qwen3.8-max 1482
+ amazon-nova-experimental-chat-12-10 1421
+ amazon-nova-experimental-chat-26-02-10 1448
+ claude-opus-5-max 1505
+ claude-sonnet-4-5-20250929-high-32k 1434
+ deepseek-r1-0528 1427
+ deepseek-v3.2-exp-thinking 1425
+ deepseek-v4-pro-high-20260813 1441
+ ernie-5.0-preview-1022 1430
+ gemini-2.5-pro 1458
+ gemini-3-flash 1467
+ gemini-3-pro 1480
+ gemini-3.5-flash-lite 1437
+ gemini-3.6-flash-high 1477
+ glm-4.5 1430
+ glm-4.7 1436
+ glm-5 1446
+ glm-5.1 1463
+ glm-5.2-max 1467
+ glm-5.3-flash 1466
+ glm-5.3-max 1475
+ gpt-5.1 1423
+ gpt-5.1-high 1442
+ gpt-5.6-terra-xhigh 1447
+ grok-4.20-beta1 1445
+ grok-4.5 1451

Benchmark Aug 22, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +23 −23

- claude-fable-5 1494
- claude-opus-4-8-high 1462
- claude-opus-5-high 1505
- claude-opus-5-max 1503
- deepseek-v3.2-thinking 1420
- deepseek-v4-pro-high-20260813 1443
- gemini-3.1-pro-preview 1479
- gemini-3.5-flash-lite 1437
- gemini-3.5-flash-medium 1476
- gemini-3.6-flash-high 1477
- gemini-3.7-flash-high 1491
- glm-5.3-max 1474
- gpt-5.5-high 1470
- gpt-5.6-terra-xhigh 1445
- hy3 1442
- kimi-k3-max 1477
- mimo-v2.5-pro 1464
- minimax-m3 1434
- muse-spark 1473
- muse-spark-1.1 1479
- muse-spark-1.2 (xHigh) 1488
- qwen3.7-plus 1457
- qwen3.8-max 1483
+ claude-fable-5 1495
+ claude-opus-4-8-high 1461
+ claude-opus-5-high 1504
+ claude-opus-5-max 1504
+ deepseek-v4-pro-high-20260813 1439
+ gemini-3.1-pro-preview 1480
+ gemini-3.5-flash-lite 1436
+ gemini-3.5-flash-medium 1475
+ gemini-3.6-flash-high 1476
+ gemini-3.7-flash-high 1490
+ glm-5.3-max 1477
+ gpt-5.5-high 1471
+ gpt-5.6-terra-xhigh 1446
+ hy3 1441
+ kimi-k3-max 1476
+ mimo-v2.5-pro 1465
+ minimax-m3 1435
+ muse-spark 1474
+ muse-spark-1.1 1478
+ muse-spark-1.2 (xHigh) 1487
+ qwen3.7-plus 1456
+ qwen3.8-27b 1441
+ qwen3.8-max 1482

Benchmark Aug 20, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +33 −33

- claude-fable-5 1493
- claude-opus-4-8-high 1461
- claude-opus-5-max 1508
- claude-sonnet-5-high 1443
- deepseek-v3.1-terminus-thinking 1420
- deepseek-v3.2-exp 1422
- deepseek-v4-flash 1431
- deepseek-v4-pro-high-preview 1446
- ernie-5.0-0110 1445
- ernie-5.0-preview-1203 1443
- gemini-3.1-pro-preview 1480
- gemini-3.5-flash-high 1482
- gemini-3.6-flash-high 1480
- glm-5.1 1463
- gpt-5.4 1452
- gpt-5.5-high 1471
- gpt-5.5-instant 1420
- gpt-5.6-luna-xhigh 1428
- gpt-5.6-sol-xhigh 1453
- gpt-5.6-terra-xhigh 1446
- grok-4.5 1451
- grok-4.6-high 1446
- hy3 1441
- inkling 1441
- kimi-k3-max 1476
- mimo-v2-pro 1436
- mimo-v2.5 1428
- mimo-v2.5-pro 1465
- minimax-m3 1435
- mistral-large-3 1429
- muse-spark-1.1 1477
- qwen3-235b-a22b-instruct-2507 1419
- qwen3.8-max 1492
+ claude-fable-5 1494
+ claude-opus-4-8-high 1462
+ claude-opus-5-max 1503
+ claude-sonnet-5-high 1442
+ deepseek-v3.2-exp 1423
+ deepseek-v4-flash 1432
+ deepseek-v4-pro-high-20260813 1443
+ deepseek-v4-pro-high-preview 1445
+ ernie-5.0-0110 1444
+ ernie-5.0-preview-1203 1442
+ gemini-3.1-pro-preview 1479
+ gemini-3.5-flash-high 1483
+ gemini-3.6-flash-high 1477
+ gemini-3.7-flash-high 1491
+ glm-5.1 1464
+ glm-5.3-max 1474
+ gpt-5.4 1453
+ gpt-5.5-high 1470
+ gpt-5.6-luna-xhigh 1429
+ gpt-5.6-sol-xhigh 1454
+ gpt-5.6-terra-xhigh 1445
+ grok-4.5 1452
+ grok-4.6-high 1444
+ hy3 1442
+ inkling 1439
+ kimi-k3-max 1477
+ mimo-v2-pro 1437

Benchmark Aug 13, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +21 −21

- amazon-nova-experimental-chat-26-02-10 1448
- claude-opus-4-5-20251101-thinking-32k 1447
- claude-opus-4-6-thinking 1503
- claude-opus-4-7 1482
- claude-opus-4-7-thinking 1490
- claude-opus-4-8-thinking 1462
- claude-sonnet-4-5-20250929-thinking-32k 1433
- deepseek-v3.1 1419
- deepseek-v3.2-exp-thinking 1425
- ernie-5.0-0110 1444
- gemini-3.1-pro-preview 1479
- gemini-3.6-flash 1479
- glm-5.1 1464
- gpt-5.4-high 1469
- gpt-5.5-high 1470
- gpt-5.5-instant 1419
- grok-4.5 1452
- inkling 1442
- kimi-k3-max 1475
- mimo-v2.5 1427
- qwen3.7-plus 1456
+ amazon-nova-experimental-chat-26-02-10 1447
+ claude-opus-4-5-20251101-high-32k 1447
+ claude-opus-4-6-high 1503
+ claude-opus-4-7 1483
+ claude-opus-4-7-high 1490
+ claude-opus-4-8-high 1461
+ claude-sonnet-4-5-20250929-high-32k 1433
+ deepseek-v3.2-exp-thinking 1424
+ ernie-5.0-0110 1445
+ gemini-3.1-pro-preview 1480
+ gemini-3.6-flash-high 1480
+ glm-5.1 1463
+ gpt-5.4-high 1470
+ gpt-5.5-high 1471
+ gpt-5.5-instant 1420
+ grok-4.5 1451
+ grok-4.6-high 1446
+ inkling 1441
+ kimi-k3-max 1476
+ mimo-v2.5 1428
+ qwen3.7-plus 1457

Benchmark Aug 11, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +49 −49

- amazon-nova-experimental-chat-26-02-10 1447
- claude-fable-5 1494
- claude-opus-4-5-20251101 1449
- claude-opus-4-5-20251101-thinking-32k 1446
- claude-opus-4-6-thinking 1502
- claude-opus-4-7 1481
- claude-opus-4-7-thinking 1489
- claude-opus-5-high 1504
- claude-opus-5-max 1506
- claude-sonnet-4-6 1457
- deepseek-v3.1 1420
- deepseek-v3.2 1424
- deepseek-v3.2-exp 1423
- deepseek-v3.2-exp-thinking 1424
- deepseek-v4-flash 1432
- deepseek-v4-flash-high-preview 1423
- deepseek-v4-pro 1450
- deepseek-v4-pro-high-preview 1445
- ernie-5.0-0110 1445
- ernie-5.0-preview-1022 1430
- ernie-5.0-preview-1203 1442
- ernie-5.1 1467
- gemini-3-flash (thinking-minimal) 1443
- gemini-3.1-pro-preview 1480
- gemini-3.5-flash-high 1480
- gemini-3.5-flash-lite 1438
- gemini-3.6-flash 1480
- gemma-4-31b 1441
- glm-4.7 1436
- glm-5.2-max 1466
- gpt-5.5-instant 1420
- gpt-5.6-luna-xhigh 1427
- gpt-5.6-terra-xhigh 1448
- grok-4.1 1437
- grok-4.1-thinking 1438
- grok-4.20-multi-agent-beta-0309 1451
- grok-4.5 1451
- hy3 1438
- inkling 1441
- kimi-k2.5-thinking 1446
- kimi-k3-max 1474
- longcat-flash-chat-2602-exp 1425
- mimo-v2.5 1428
- mimo-v2.5-pro 1464
- minimax-m3 1436
- muse-spark-1.1 1476
- qwen3.7-max-preview 1475
- qwen3.7-plus 1457
- qwen3.8-max 1497
+ amazon-nova-experimental-chat-26-02-10 1448
+ claude-fable-5 1493
+ claude-opus-4-5-20251101 1450
+ claude-opus-4-5-20251101-thinking-32k 1447
+ claude-opus-4-6-thinking 1503
+ claude-opus-4-7 1482
+ claude-opus-4-7-thinking 1490
+ claude-opus-5-high 1505
+ claude-opus-5-max 1508
+ claude-sonnet-4-6 1458
+ deepseek-v3.1 1419

Benchmark Aug 7, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +38 −38

- claude-fable-5 1496
- claude-opus-4-1-20250805-thinking-16k 1418
- claude-opus-4-5-20251101-thinking-32k 1447
- claude-opus-4-6-thinking 1503
- claude-opus-4-8 1453
- claude-opus-4-8-thinking 1463
- claude-opus-5-high 1503
- claude-opus-5-max 1507
- deepseek-v3.1 1419
- deepseek-v4-flash 1431
- deepseek-v4-flash-high-preview 1424
- deepseek-v4-pro 1451
- deepseek-v4-pro-high-preview 1444
- ernie-5.1 1468
- gemini-2.5-pro 1458
- gemini-3-pro 1480
- gemini-3.1-pro-preview 1479
- gemini-3.5-flash-high 1479
- gemini-3.5-flash-lite 1436
- gemini-3.5-flash-medium 1475
- gemini-3.6-flash 1478
- glm-5.1 1465
- glm-5.2-max 1464
- gpt-5.4-high 1470
- gpt-5.5 1465
- grok-4.5 1452
- hy3 1441
- inkling 1440
- kimi-k2.5-instant 1421
- kimi-k2.5-thinking 1445
- mimo-v2.5 1427
- mimo-v2.5-pro 1462
- minimax-m3 1437
- mistral-large-3 1430
- muse-spark-1.1 1478
- qwen3-next-80b-a3b-instruct 1419
- qwen3.7-plus 1459
- qwen3.8-max 1496
+ claude-fable-5 1494
+ claude-opus-4-5-20251101-thinking-32k 1446
+ claude-opus-4-6-thinking 1502
+ claude-opus-4-8 1452
+ claude-opus-4-8-thinking 1462
+ claude-opus-5-high 1504
+ claude-opus-5-max 1506
+ deepseek-v3.1 1420
+ deepseek-v4-flash 1432
+ deepseek-v4-flash-high-preview 1423
+ deepseek-v4-pro 1450
+ deepseek-v4-pro-high-preview 1445
+ ernie-5.1 1467
+ gemini-2.5-pro 1457
+ gemini-3-pro 1479
+ gemini-3.1-pro-preview 1480
+ gemini-3.5-flash-high 1480
+ gemini-3.5-flash-lite 1438
+ gemini-3.5-flash-medium 1476
+ gemini-3.6-flash 1480
+ glm-5.1 1464
+ glm-5.2-max 1466

Benchmark Aug 4, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +2 −2

- gemini-3.5-flash-high 1480
- kimi-k3-max 1473
+ claude-opus-4-1-20250805-thinking-16k 1418
+ gemini-3.5-flash-high 1479

Benchmark Aug 3, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +30 −30

- claude-fable-5 1494
- claude-opus-4-1-20250805-thinking-16k 1418
- claude-opus-4-7 1482
- claude-opus-4-7-thinking 1490
- claude-opus-5-high 1505
- claude-opus-5-max 1512
- claude-sonnet-5-high 1440
- deepseek-v4-flash 1432
- deepseek-v4-flash-thinking 1423
- deepseek-v4-pro 1450
- deepseek-v4-pro-thinking 1445
- gemini-3-pro 1479
- gemini-3.5-flash-lite 1439
- gemini-3.5-flash-medium 1473
- gemini-3.6-flash 1477
- gemma-4-31b 1442
- gpt-5.5-high 1469
- gpt-5.6-luna-xhigh 1429
- gpt-5.6-sol-xhigh 1455
- gpt-5.6-terra-xhigh 1449
- grok-4.20-beta-0309-reasoning 1452
- grok-4.5 1451
- hy3 1442
- inkling 1442
- kimi-k2.5-instant 1420
- minimax-m3 1436
- mistral-large-3 1429
- muse-spark-1.1 1479
- qwen3.5-397b-a17b 1439
- qwen3.7-plus 1456
+ claude-fable-5 1496
+ claude-opus-4-7 1481
+ claude-opus-4-7-thinking 1489
+ claude-opus-5-high 1503
+ claude-opus-5-max 1507
+ claude-sonnet-5-high 1443
+ deepseek-v4-flash 1431
+ deepseek-v4-flash-high-preview 1424
+ deepseek-v4-pro 1451
+ deepseek-v4-pro-high-preview 1444
+ gemini-3-pro 1480
+ gemini-3.5-flash-lite 1436
+ gemini-3.5-flash-medium 1475
+ gemini-3.6-flash 1478
+ gemma-4-31b 1441
+ gpt-5.5-high 1470
+ gpt-5.6-luna-xhigh 1427
+ gpt-5.6-sol-xhigh 1453
+ gpt-5.6-terra-xhigh 1448
+ grok-4.20-beta-0309-reasoning 1451
+ grok-4.5 1452
+ hy3 1441
+ inkling 1440
+ kimi-k2.5-instant 1421
+ minimax-m3 1437
+ mistral-large-3 1430
+ muse-spark-1.1 1478
+ qwen3.5-397b-a17b 1438
+ qwen3.7-plus 1459
+ qwen3.8-max 1496

Benchmark Jul 31, 2026, 6:01 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +2 −2

- gpt-4.5-preview-2025-02-27 1417
- qwen3.5-122b-a10b 1418
+ gpt-5.6-luna-xhigh 1429
+ gpt-5.6-terra-xhigh 1449

Benchmark Jul 30, 2026, 12:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +83 −83

- claude-fable-5 1504
- claude-fable-5 1485
- claude-fable-5 1472
- claude-opus-4-6 1506
- claude-opus-4-6 1487
- claude-opus-4-6 1472
- claude-opus-4-6-thinking 1512
- claude-opus-4-6-thinking 1493
- claude-opus-4-6-thinking 1478
- claude-opus-4-6-thinking 1465
- claude-opus-4-7 1492
- claude-opus-4-7 1474
- claude-opus-4-7-thinking 1499
- claude-opus-4-7-thinking 1477
- claude-opus-4-8-thinking 1469
- claude-opus-4-8-thinking 1467
- claude-opus-5-high 1515
- claude-opus-5-high 1494
- claude-opus-5-high 1477
- claude-opus-5-max 1522
- claude-opus-5-max 1504
- claude-opus-5-max 1484
- gemini-2.5-flash 1465
- gemini-3-pro 1490
- gemini-3-pro 1481
- gemini-3-pro 1472
- gemini-3-pro 1465
- gemini-3.1-pro-preview 1489
- gemini-3.5-flash-high 1490
- gemini-3.5-flash-high 1477
- gemini-3.5-flash-medium 1482
- gemini-3.6-flash 1488
- gemini-3.6-flash 1473
- gpt-5-high 1465
- gpt-5.1 1485
- gpt-5.1 1472
- gpt-5.1-high 1482
- gpt-5.1-high 1474
- gpt-5.1-high 1466
- gpt-5.2 1487
- gpt-5.2 1475
- gpt-5.2-high 1493
- gpt-5.2-high 1476
- gpt-5.3-chat-latest 1484
- gpt-5.4 1499
- gpt-5.4 1493
- gpt-5.4 1486
- gpt-5.4 1476
- gpt-5.4-high 1495
- gpt-5.4-high 1492
- gpt-5.4-high 1490
- gpt-5.4-high 1486
- gpt-5.4-mini-high 1495
- gpt-5.4-mini-high 1483
- gpt-5.4-mini-high 1469
- gpt-5.4-nano-high 1482
- gpt-5.4-nano-high 1467
- gpt-5.5 1491
- gpt-5.5 1488
- gpt-5.5 1485

Benchmark Jul 28, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +42 −41

- claude-fable-5 1493
- claude-opus-4-6 1507
- claude-opus-4-6-thinking 1477
- claude-opus-4-7-thinking 1489
- claude-opus-4-7-thinking 1476
- gemini-3.1-pro-preview 1471
- gemini-3.5-flash-high 1464
- gemini-3.5-flash-medium 1485
- gemini-3.5-flash-medium 1475
- gemini-3.6-flash 1491
- gemini-3.6-flash 1481
- gemini-3.6-flash 1475
- gpt-5.2 1486
- gpt-5.2-chat-latest-20260210 1465
- gpt-5.4 1494
- gpt-5.4-high 1494
- gpt-5.4-high 1489
- gpt-5.4-high 1485
- gpt-5.4-high 1480
- gpt-5.4-high 1470
- gpt-5.4-mini-high 1496
- gpt-5.4-mini-high 1484
- gpt-5.4-mini-high 1470
- gpt-5.5 1490
- gpt-5.5-high 1480
- gpt-5.5-high 1469
- gpt-5.5-instant 1466
- gpt-5.6-sol-xhigh 1486
- gpt-5.6-sol-xhigh 1480
- gpt-5.6-sol-xhigh 1475
- grok-4.5 1473
- kimi-k3 1482
- kimi-k3 1473
- kimi-k3 1472
- muse-spark-1.1 1491
- muse-spark-1.1 1483
- muse-spark-1.1 1474
- qwen3.5-max-preview 1474
- qwen3.5-max-preview 1470
- qwen3.5-max-preview 1468
- qwen3.7-max-preview 1476
+ claude-fable-5 1494
+ claude-opus-4-6 1506
+ claude-opus-4-6-thinking 1478
+ claude-opus-4-7-thinking 1490
+ claude-opus-4-7-thinking 1477
+ claude-opus-5-high 1515
+ claude-opus-5-high 1505
+ claude-opus-5-high 1494
+ claude-opus-5-high 1477
+ claude-opus-5-max 1522
+ claude-opus-5-max 1512
+ claude-opus-5-max 1504
+ claude-opus-5-max 1484
+ gemini-3.5-flash-medium 1482
+ gemini-3.5-flash-medium 1473
+ gemini-3.6-flash 1488
+ gemini-3.6-flash 1477
+ gemini-3.6-flash 1473
+ gpt-5.2 1487

Benchmark Jul 22, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +34 −35

- claude-fable-5 1489
- claude-fable-5 1477
- claude-fable-5 1466
- claude-opus-4-6-thinking 1502
- claude-opus-4-6-thinking 1492
- claude-opus-4-8-thinking 1472
- claude-opus-4-8-thinking 1470
- claude-opus-4-8-thinking 1468
- claude-opus-4-8-thinking 1466
- ernie-5.1 1477
- ernie-5.1 1468
- gemini-3-pro 1480
- gpt-5.2 1487
- gpt-5.2-high 1477
- gpt-5.4 1487
- gpt-5.4 1477
- gpt-5.4-high 1486
- gpt-5.5 1491
- gpt-5.5 1480
- gpt-5.5-high 1487
- gpt-5.5-high 1483
- gpt-5.5-high 1479
- gpt-5.5-instant 1465
- gpt-5.6-sol-xhigh 1487
- gpt-5.6-sol-xhigh 1481
- gpt-5.6-sol-xhigh 1476
- gpt-5.6-sol-xhigh 1471
- grok-4.5 1476
- grok-4.5 1471
- grok-4.5 1467
- kimi-k3 1483
- kimi-k3 1474
- muse-spark 1482
- muse-spark-1.1 1476
- qwen3.7-max-preview 1473
+ claude-fable-5 1485
+ claude-fable-5 1472
+ claude-opus-4-6-thinking 1503
+ claude-opus-4-6-thinking 1493
+ claude-opus-4-6-thinking 1465
+ claude-opus-4-8-thinking 1469
+ claude-opus-4-8-thinking 1467
+ gemini-2.5-flash 1465
+ gemini-3-pro 1479
+ gemini-3.1-pro-preview 1471
+ gemini-3.6-flash 1491
+ gemini-3.6-flash 1481
+ gemini-3.6-flash 1475
+ gpt-5.2 1486
+ gpt-5.2-high 1476
+ gpt-5.4 1486
+ gpt-5.4 1476
+ gpt-5.4-high 1485
+ gpt-5.5 1490
+ gpt-5.5 1481
+ gpt-5.5-high 1484
+ gpt-5.5-high 1480
+ gpt-5.5-instant 1466
+ gpt-5.6-sol-xhigh 1486
+ gpt-5.6-sol-xhigh 1480

Benchmark Jul 21, 2026, 6:01 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +87 −87

- amazon-nova-experimental-chat-11-10 1416
- amazon-nova-experimental-chat-12-10 1420
- amazon-nova-experimental-chat-26-02-10 1448
- chatgpt-4o-latest-20250326 1429
- claude-opus-4-1-20250805 1417
- claude-opus-4-1-20250805-thinking-16k 1419
- claude-opus-4-5-20251101 1450
- claude-opus-4-5-20251101-thinking-32k 1447
- claude-opus-4-6-thinking 1501
- claude-opus-4-7-thinking 1490
- claude-opus-4-8 1454
- claude-opus-4-8-thinking 1462
- claude-sonnet-4-5-20250929 1438
- claude-sonnet-4-5-20250929-thinking-32k 1433
- claude-sonnet-4-6 1457
- claude-sonnet-5-high 1442
- deepseek-r1-0528 1428
- deepseek-v3.1 1419
- deepseek-v3.1-terminus 1417
- deepseek-v3.1-terminus-thinking 1420
- deepseek-v3.1-thinking 1417
- deepseek-v3.2 1424
- deepseek-v3.2-exp 1423
- deepseek-v3.2-exp-thinking 1424
- deepseek-v3.2-thinking 1420
- deepseek-v4-flash 1433
- deepseek-v4-flash-thinking 1424
- deepseek-v4-pro 1450
- deepseek-v4-pro-thinking 1446
- dola-seed-2.0-pro 1448
- ernie-5.0-0110 1445
- ernie-5.0-preview-1022 1430
- ernie-5.0-preview-1203 1442
- gemini-2.5-flash 1417
- gemini-2.5-pro 1457
- gemini-3-flash 1466
- gemini-3-flash (thinking-minimal) 1444
- gemma-4-26b-a4b 1434
- gemma-4-31b 1442
- glm-4.5 1429
- glm-4.6 1440
- glm-4.7 1436
- glm-5 1445
- glm-5.1 1466
- glm-5.2 (max) 1463
- glm-5v-turbo 1442
- gpt-4.5-preview-2025-02-27 1417
- gpt-5.1 1422
- gpt-5.1-high 1441
- gpt-5.2-chat-latest-20260210 1438
- gpt-5.4 1453
- gpt-5.5 1464
- gpt-5.5-high 1470
- gpt-5.5-instant 1419
- gpt-5.6-sol-xhigh 1457
- grok-3-preview-02-24 1425
- grok-4.1 1436
- grok-4.1-thinking 1437
- grok-4.20-beta-0309-reasoning 1452
- grok-4.20-beta1 1444

Benchmark Jul 17, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +33 −33

- claude-fable-5 1495
- claude-opus-4-1-20250805-thinking-16k 1418
- claude-opus-4-5-20251101 1449
- claude-opus-4-6 1498
- claude-opus-4-8 1453
- claude-opus-4-8-thinking 1461
- claude-sonnet-5-high 1443
- deepseek-v4-pro 1449
- deepseek-v4-pro-thinking 1447
- dola-seed-2.0-pro 1447
- ernie-5.1 1467
- gemini-3.1-flash-lite-preview 1415
- gemini-3.5-flash-medium 1477
- glm-5.1 1467
- glm-5.2 (max) 1460
- glm-5v-turbo 1443
- gpt-5.2-high 1416
- gpt-5.4 1452
- gpt-5.4-high 1468
- gpt-5.5 1463
- gpt-5.5-high 1469
- gpt-5.6-sol-xhigh 1458
- grok-4.1 1437
- grok-4.20-beta-0309-reasoning 1453
- grok-4.20-multi-agent-beta-0309 1450
- grok-4.5 1455
- kimi-k2.5-thinking 1444
- kimi-k2.6 1456
- longcat-flash-chat-2602-exp 1426
- mimo-v2.5 1427
- muse-spark-1.1 1478
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 1441
- qwen3.7-max-preview 1475
+ claude-fable-5 1493
+ claude-opus-4-1-20250805-thinking-16k 1419
+ claude-opus-4-5-20251101 1450
+ claude-opus-4-6 1497
+ claude-opus-4-8 1454
+ claude-opus-4-8-thinking 1462
+ claude-sonnet-5-high 1442
+ deepseek-v4-pro 1450
+ deepseek-v4-pro-thinking 1446
+ dola-seed-2.0-pro 1448
+ ernie-5.1 1468
+ gemini-3.5-flash-medium 1475
+ glm-5.1 1466
+ glm-5.2 (max) 1463
+ glm-5v-turbo 1442
+ gpt-5.4 1453
+ gpt-5.4-high 1470
+ gpt-5.5 1464
+ gpt-5.5-high 1470
+ gpt-5.6-sol-xhigh 1457
+ grok-4.1 1436
+ grok-4.20-beta-0309-reasoning 1452
+ grok-4.20-multi-agent-beta-0309 1449
+ grok-4.5 1452
+ inkling 1444
+ kimi-k2.5-thinking 1445
+ kimi-k2.6 1455

Benchmark Jul 11, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +36 −36

- claude-opus-4-5-20251101 1450
- claude-opus-4-7-thinking 1489
- claude-opus-4-8 1454
- claude-opus-4-8-thinking 1463
- claude-sonnet-5-thinking 1445
- deepseek-v3.1-terminus 1418
- deepseek-v4-flash 1431
- deepseek-v4-flash-thinking 1423
- deepseek-v4-pro 1450
- dola-seed-2.0-pro 1448
- gemini-3-pro 1479
- gemini-3.1-pro-preview 1480
- gemini-3.5-flash 1482
- gemma-4-31b 1441
- glm-5.2 (max) 1463
- gpt-5.4 1453
- gpt-5.4-high 1470
- gpt-5.4-mini-high 1413
- grok-4.1 1436
- grok-4.1-thinking 1438
- grok-4.20-beta-0309-reasoning 1454
- kimi-k2-thinking-turbo 1414
- kimi-k2.5-thinking 1445
- kimi-k2.6 1455
- longcat-flash-chat-2602-exp 1425
- mimo-v2-flash (non-thinking) 1411
- mimo-v2.5 1426
- minimax-m3 1439
- mistral-large-3 1430
- mistral-medium-3.5 1420
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 1438
- qwen3-235b-a22b-thinking-2507 1414
- qwen3-max-2025-09-23 1413
- qwen3.5-397b-a17b 1439
- qwen3.6-plus 1437
- qwen3.7-plus 1462
+ claude-opus-4-5-20251101 1449
+ claude-opus-4-7-thinking 1490
+ claude-opus-4-8 1453
+ claude-opus-4-8-thinking 1461
+ claude-sonnet-5-high 1443
+ deepseek-v3.1-terminus 1417
+ deepseek-v4-flash 1433
+ deepseek-v4-flash-thinking 1424
+ deepseek-v4-pro 1449
+ dola-seed-2.0-pro 1447
+ gemini-3-pro 1480
+ gemini-3.1-pro-preview 1479
+ gemini-3.5-flash-high 1480
+ gemini-3.5-flash-medium 1477
+ gemma-4-31b 1442
+ glm-5.2 (max) 1460
+ glm-5v-turbo 1443
+ gpt-5.4 1452
+ gpt-5.4-high 1468
+ gpt-5.6-sol-xhigh 1458
+ grok-4.1 1437
+ grok-4.1-thinking 1437
+ grok-4.20-beta-0309-reasoning 1453
+ grok-4.5 1455

Benchmark Jul 3, 2026, 6:02 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +21 −21

- claude-fable-5 1494
- claude-opus-4-6-thinking 1500
- claude-opus-4-8 1456
- deepseek-v4-pro 1449
- deepseek-v4-pro-thinking 1446
- gemini-3.5-flash 1480
- gemma-4-26b-a4b 1435
- glm-5 1446
- glm-5.1 1468
- glm-5.2 (max) 1465
- gpt-5.2 1411
- gpt-5.4 1454
- gpt-5.5-high 1468
- grok-4.1-thinking 1437
- grok-4.20-beta-0309-reasoning 1455
- mimo-v2-omni 1423
- mimo-v2.5 1427
- minimax-m3 1440
- muse-spark 1472
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 1439
- qwen3.7-plus 1463
+ claude-fable-5 1495
+ claude-opus-4-6-thinking 1501
+ claude-opus-4-8 1454
+ claude-sonnet-5-thinking 1445
+ deepseek-v4-pro 1450
+ deepseek-v4-pro-thinking 1447
+ gemini-3.5-flash 1482
+ gemma-4-26b-a4b 1434
+ glm-5 1445
+ glm-5.1 1467
+ glm-5.2 (max) 1463
+ gpt-5.4 1453
+ gpt-5.5-high 1469
+ grok-4.1-thinking 1438
+ grok-4.20-beta-0309-reasoning 1454
+ mimo-v2-omni 1422
+ mimo-v2.5 1426
+ minimax-m3 1439
+ muse-spark 1473
+ nvidia-nemotron-3-ultra-550b-a55b-nvfp4 1438
+ qwen3.7-plus 1462

Benchmark Jun 27, 2026, 6:01 AM

LMArena (text) scores changed

Arena Elo (text, overall) updated.

View raw diff +29 −29

- claude-opus-4-5-20251101 1449
- claude-opus-4-5-20251101-thinking-32k 1446
- claude-opus-4-6-thinking 1501
- claude-opus-4-7 1481
- claude-opus-4-8 1455
- claude-opus-4-8-thinking 1462
- claude-sonnet-4-6 1456
- deepseek-v4-flash 1430
- deepseek-v4-flash-thinking 1422
- deepseek-v4-pro 1448
- deepseek-v4-pro-thinking 1447
- gemini-3-flash (thinking-minimal) 1445
- gemma-4-26b-a4b 1434
- glm-5.1 1470
- glm-5.2 (max) 1467
- gpt-5.4-mini-high 1412
- grok-4-0709 1410
- grok-4.1 1437
- grok-4.20-beta-0309-reasoning 1453
- grok-4.20-multi-agent-beta-0309 1451
- kimi-k2.5-instant 1420
- kimi-k2.6 1454
- mimo-v2.5 1426
- minimax-m3 1442
- mistral-medium-3.5 1419
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 1435
- qwen3.5-397b-a17b 1440
- qwen3.6-max-preview 1447
- qwen3.6-plus 1438
+ claude-opus-4-5-20251101 1450
+ claude-opus-4-5-20251101-thinking-32k 1447
+ claude-opus-4-6-thinking 1500
+ claude-opus-4-7 1482
+ claude-opus-4-8 1456
+ claude-opus-4-8-thinking 1463
+ claude-sonnet-4-6 1457
+ deepseek-v4-flash 1431
+ deepseek-v4-flash-thinking 1423
+ deepseek-v4-pro 1449
+ deepseek-v4-pro-thinking 1446
+ gemini-3-flash (thinking-minimal) 1444
+ gemma-4-26b-a4b 1435
+ glm-5.1 1468
+ glm-5.2 (max) 1465
+ gpt-5.4-mini-high 1413
+ grok-4.1 1436
+ grok-4.20-beta-0309-reasoning 1455
+ grok-4.20-multi-agent-beta-0309 1450
+ kimi-k2.5-instant 1421
+ kimi-k2.6 1455
+ mimo-v2.5 1427
+ minimax-m3 1440
+ mistral-medium-3.5 1420
+ nvidia-nemotron-3-ultra-550b-a55b-nvfp4 1439
+ qwen3.5-397b-a17b 1439
+ qwen3.6-max-preview 1446
+ qwen3.6-plus 1437
+ qwen3.7-plus 1463