Arena — Text
Shown as Arena publishes it: their metrics, their models. A model name opens its page here; the arrow opens the original board.
- Published by
- Arena
- License
- not stated
- Updates
- continuous
- Data as of
- 2026-10-08
- Fetched
- 2026-10-08
- Entries
- 414 · 44 unmatched
- Gemini 4 Argon
1525 - Claude Opus 5.5
1507 - Claude Opus 4.6 1504
- Claude Fable 5 1504
- Claude Opus 4.7 1501
- Claude Fable 5.1 1501
- Gemini 3.8 Flash 1497
- Muse Spark 1.3
1494 - Muse Spark 1.2 1492
- Muse Spark 1.1 1491
- Claude Opus 5 1490
- Muse Spark 1489
An Elo score has no zero, so each row is a dot on a scale from 1485: read the distance between dots, not from the left edge.
414 scored
| # | Model | |
|---|---|---|
| 1 | Gemini 4 ArgonhighGoogle | 15251517–1534 |
| 2 | Claude Opus 5.5highAnthropic | 15071499–1515 |
| 3 | Claude Opus 4.6highAnthropic | 15041501–1508 |
| 4 | Claude Fable 5highAnthropic | 15041499–1508 |
| 5 | Claude Opus 4.7highAnthropic | 15011497–1505 |
| 6 | Claude Fable 5.1maxAnthropic | 15011494–1507 |
| 7 | Claude Opus 4.6Anthropic | 14981494–1501 |
| 8 | Gemini 3.8 FlashhighGoogle | 14971492–1501 |
| 9 | Muse Spark 1.3maxMeta | 14941488–1500 |
| 10 | Claude Opus 4.7Anthropic | 14941490–1498 |
| 11 | Muse Spark 1.2xhighMeta | 14921484–1500 |
| 12 | Muse Spark 1.1Meta | 14911486–1495 |
| 13 | Claude Opus 5highAnthropic | 14901486–1494 |
| 14 | Claude Opus 5maxAnthropic | 14891485–1494 |
| 15 | Muse SparkMeta | 14891483–1495 |
| 16 |  Kimi K3maxKimi | 14881483–1493 |
| 17 | Gemini 3.1 PropreviewGoogle | 14871484–1490 |
| 18 | Gemini 3.7 FlashhighGoogle | 14861481–1492 |
| 19 | Gemini 3 ProGoogle | 14851482–1489 |
| 20 |  GPT 5.6 SolxhighOpenAI | 14851481–1489 |
| 21 | GPT 6.1 SolmaxOpenAI | 14841475–1493 |
| 22 |  Qwen 3.8 MaxAlibaba | 14831478–1488 |
| 23 | Gemini 3.6 FlashhighGoogle | 14821478–1487 |
| 24 | GPT 5.5highOpenAI | 14821478–1485 |
| 25 | Claude Opus 4.8highAnthropic | 14811478–1485 |
| 26 |  MiMo V2.6 ProXiaomi | 14801471–1490 |
| 27 |  GLM 5.3maxZ AI | 14781473–1484 |
| 28 | Gemini 3.5 FlashhighGoogle | 14781474–1481 |
| 29 | GPT 5.5OpenAI | 14771473–1480 |
| 30 | Gemini 3.5 FlashmediumGoogle | 14761472–1480 |
| 31 | GPT 5.220260210 · chatOpenAI | 14761472–1480 |
| 32 | Claude Sonnet 5.5xhighAnthropic | 14761467–1485 |
| 33 | GLM 5.2maxZ AI | 14751471–1479 |
| 34 | GPT 5.4highOpenAI | 14751471–1479 |
| 35 | GPT 6 AstramaxOpenAI | 14751469–1482 |
| 36 | Qwen 3.7 MaxpreviewAlibaba | 14751465–1485 |
| 37 |  Grok 4.20beta1SpaceXAI | 14751470–1479 |
| 38 | GLM 5.3 FlashZ AI | 14751470–1480 |
| 39 |  DeepSeek V4.1 FlashmaxDeepSeek | 14751468–1481 |
| 40 | Claude Opus 4.8Anthropic | 14741470–1478 |
| 41 | Claude Opus 4.520251101 · high · 32000Anthropic | 14741470–1478 |
| 42 | GPT 5.5 InstantOpenAI | 14731468–1478 |
| 43 | Gemini 3 FlashGoogle | 14731469–1477 |
| 44 | Claude Sonnet 4.6Anthropic | 14721468–1476 |
| 45 | Grok 4.20beta · 0309 · onSpaceXAI | 14721468–1475 |
| 46 | Grok 4.20beta · 0309 · multi-agentSpaceXAI | 14701467–1474 |
| 47 | Claude Opus 4.520251101Anthropic | 14701467–1473 |
| 48 | MiMo V2.5 ProXiaomi | 14681464–1471 |
| 49 |  ERNIE 5.1Baidu | 14671463–1472 |
| 50 | GPT 5.6 TerraxhighOpenAI | 14661462–1470 |
| 51 | Grok 4.5SpaceXAI | 14661461–1470 |
| 52 | Grok 4.1onSpaceXAI | 14651462–1468 |
| 53 | GPT 5.4OpenAI | 14651461–1468 |
| 54 | Qwen 3.5 MaxpreviewAlibaba | 14651460–1470 |
| 55 | DeepSeek V4 Pro20260813 · highDeepSeek | 14651458–1471 |
| 56 | GLM 5.1Z AI | 14641461–1468 |
| 57 | Claude Sonnet 5highAnthropic | 14611457–1465 |
| 58 | Kimi K2.6Kimi | 14611456–1465 |
| 59 | Qwen 3.6 MaxpreviewAlibaba | 14601452–1469 |
| 60 | Grok 4.1SpaceXAI | 14591456–1462 |
| 61 | Gemini 3 Flashon · minimalGoogle | 14581455–1461 |
| 62 | DeepSeek V4 ProDeepSeek | 14581454–1462 |
| 63 | GLM 5Z AI | 14581453–1462 |
| 64 | Claude Sonnet 4.520250929 · high · 32000Anthropic | 14561454–1459 |
| 65 |  dola seed 2.0 proByteDance | 14561453–1460 |
| 66 | Qwen 3.7 PlusAlibaba | 14561452–1460 |
| 67 | GPT 6 SolmaxOpenAI | 14561449–1463 |
| 68 | GPT 5.1highOpenAI | 14561452–1459 |
| 69 | Claude Sonnet 4.520250929Anthropic | 14551452–1458 |
| 70 | Gemini 3.5 Flash LiteGoogle | 14551451–1460 |
| 71 | DeepSeek V4 Propreview · highDeepSeek | 14551451–1459 |
| 72 | Grok 4.6highSpaceXAI | 14541449–1459 |
| 73 |  Hunyuan Hy3Tencent | 14541448–1461 |
| 74 | GPT 5.6 LunaxhighOpenAI | 14521448–1457 |
| 75 | Gemma 431BGoogle | 14521445–1460 |
| 76 | MiMo V2.6 FlashXiaomi | 14511444–1458 |
| 77 | GPT 5.3chatOpenAI | 14501446–1454 |
| 78 | Kimi K2.5onKimi | 14501447–1453 |
| 79 | Claude Opus 4.120250805 · on · 16000Anthropic | 14501446–1453 |
| 80 | ERNIE 5.0preview · 1203Baidu | 14491442–1455 |
| 81 | Claude Opus 4.120250805Anthropic | 14481445–1451 |
| 82 | MiMo V2 ProXiaomi | 14481443–1452 |
| 83 |  Step 5previewStepFun | 14471439–1456 |
| 84 | GPT 5.4 minihighOpenAI | 14471443–1451 |
| 85 | ERNIE 5.00110Baidu | 14461442–1450 |
| 86 | Gemini 2.5 ProGoogle | 14451443–1448 |
| 87 | GPT 4.5preview · 2025-02-27OpenAI | 14451439–1450 |
| 88 | Qwen 3.6 PlusAlibaba | 14431439–1447 |
| 89 | GPT 4o (ChatGPT)20250326OpenAI | 14431440–1446 |
| 90 | Grok 4.7xhighSpaceXAI | 14431436–1450 |
| 91 | GPT 6 LunamaxOpenAI | 14431438–1448 |
| 92 | Qwen 3.5397B A17BAlibaba | 14421439–1445 |
| 93 | Grok 4.3SpaceXAI | 14421438–1445 |
| 94 | GLM 4.7Z AI | 14411435–1447 |
| 95 |  InklingThinking Machines | 14411437–1445 |
| 96 |  MiniMax M3MiniMax | 14401437–1444 |
| 97 | DeepSeek V4 Flashpreview · highDeepSeek | 14391435–1443 |
| 98 | GPT 5.1OpenAI | 14391435–1442 |
| 99 | Qwen 3.827BAlibaba | 14381433–1443 |
| 100 | Gemma 426B A4BGoogle | 14381430–1445 |
What each column measures
- Overall (style control)
- Higher is better · General preference