AI leaderboard · Overall
Best AI models overall: 421 models ranked by blind votes
Every text prompt on the arena, scored with style control so that a longer or more heavily formatted answer does not win on looks alone. Ranked by LMArena’s blind votes, every score with its margin of error and, beside it, the list price of each model on our price list.
Run Gemini 4 Argon up to 50% below list price. $25 a month brings $110 of API credit and cancels any time; $25 once buys $100. Scores from LMArena, published 9 November 2026, under CC BY 4.0. Prices from each maker’s pricing page, read on 12 November 2026.
1526Gemini 4 Carbon from Google
- Models ranked
- 421
- Level with the leader
- 2
- On our price list
- 43
- Published
- 9 November 2026
Level: the votes cannot separate it from the leader.
On LMArena’s Overall board, Gemini 4 Carbon from Google leads with 1526 points from 4,282 blind votes, published 9 November 2026. 2 other models are statistically level with it. It also tops the models with an API price, at $4 per million tokens with input and output weighed 3 to 1.
Run models from this ranking below list price
AIGROW API credit runs these models through one key, billed per token at the rates below. $25 a month brings $110 of API credit and cancels any time; $25 once buys $100.
- No. 2Gemini 4 ArgonGoogle
List price $2.00 / $10.00$1.00 / $5.00with AIGROW API creditRun Gemini 4 Argon up to 50% below list priceCertified genuine by AIGROW on 11 November 2026 - No. 4Claude Opus 5.5Anthropic
List price $4.00 / $20.00$1.60 / $8.00with AIGROW API creditRun Claude Opus 5.5 up to 60% below list priceCertified genuine by AIGROW on 11 November 2026 - No. 7Claude Fable 5.1Anthropic
List price $10.00 / $50.00$4.00 / $20.00with AIGROW API creditRun Claude Fable 5.1 up to 60% below list priceCertified genuine by AIGROW on 11 November 2026
US dollars per million input / output tokens. Certified genuine by AIGROW means the model passed AIGROW’s own check against the same model at its maker on 11 November 2026. No model maker reviewed or endorsed it.
Best AI models overall
Every text prompt on the arena, scored with style control so that a longer or more heavily formatted answer does not win on looks alone.
| # | Model | Score | Votes | Per 1M tokens, in / out |
|---|---|---|---|---|
| 1 | Gemini 4 CarbonGoogle · Gemini 4 Carbon (High) | 95% interval 1516 to 1536 | 4,282 | $2.00 / $10.00 |
| 2 | Gemini 4 ArgonGoogle · Gemini 4 Argon (High)Run Gemini 4 Argon up to 50% below list priceCertified genuine by AIGROW on 11 November 2026 | 95% interval 1517 to 1528Its interval overlaps 1 model above it | 19,787 | |
| 3 | Muse WonderMeta · Muse Wonder (Max) | 95% interval 1505 to 1517Its interval overlaps 2 models above it | 12,032 | $4.00 / $20.00 |
| 4 | Claude Opus 5.5Anthropic · Claude Opus 5.5 (High)Run Claude Opus 5.5 up to 60% below list priceCertified genuine by AIGROW on 11 November 2026 | 95% interval 1500 to 1512Its interval overlaps 1 model above it | 15,249 | |
| 5 | Claude Fable 5 (High)Anthropic | 95% interval 1500 to 1508Its interval overlaps 2 models above it | 45,524 | No list price |
| 6 | Claude Opus 4.6 (High)Anthropic | 95% interval 1500 to 1506Its interval overlaps 3 models above it | 84,424 | No list price |
| 7 | Claude Fable 5.1Anthropic · Claude Fable 5.1 (Max)Run Claude Fable 5.1 up to 60% below list priceCertified genuine by AIGROW on 11 November 2026 | 95% interval 1497 to 1508Its interval overlaps 4 models above it | 20,087 | |
| 8 | Claude Opus 4.7 (High)Anthropic | 95% interval 1497 to 1505Its interval overlaps 5 models above it | 64,308 | No list price |
| 9 | Gemini 3.8 FlashGoogle · Gemini 3.8 Flash (High) | 95% interval 1493 to 1502Its interval overlaps 5 models above it | 61,143 | $0.75 / $3.75 |
| 10 | Claude Opus 4.6Anthropic | 95% interval 1493 to 1500Its interval overlaps 3 models above it | 89,228 | No list price |
| 11 | Muse Spark 1.3Meta · Muse Spark 1.3 (Max) | 95% interval 1491 to 1501Its interval overlaps 7 models above it | 26,111 | $1.25 / $4.25 |
| 12 | Claude Opus 4.7Anthropic | 95% interval 1490 to 1498Its interval overlaps 5 models above it | 65,369 | No list price |
| 13 | Muse Spark 1.2 (xHigh)Meta | 95% interval 1488 to 1499Its interval overlaps 6 models above it | 15,004 | No list price |
| 14 | Muse Spark 1.1Meta | 95% interval 1487 to 1495Its interval overlaps 5 models above it | 45,562 | No list price |
| 15 | Claude Opus 5Anthropic · Claude Opus 5 (High) | 95% interval 1486 to 1493Its interval overlaps 6 models above it | 73,697 | $5.00 / $25.00 |
| 16 | Gemini 3.7 Flash (High)Google | 95% interval 1485 to 1494Its interval overlaps 7 models above it | 33,300 | No list price |
| 17 | Muse SparkMeta | 95% interval 1483 to 1495Its interval overlaps 8 models above it | 14,009 | No list price |
| 18 | Claude Opus 5Anthropic · Claude Opus 5 (Max) | 95% interval 1484 to 1494Its interval overlaps 9 models above it | 35,710 | $5.00 / $25.00 |
| 19 | Kimi K3Moonshot AI · Kimi K3 (Max) · open weights | 95% interval 1483 to 1491Its interval overlaps 8 models above it | 40,867 | $3.00 / $15.00 |
| 20 | Gemini 3.1 Pro (preview)Google · Gemini 3.1 Pro Preview | 95% interval 1484 to 1490Its interval overlaps 7 models above it | 132,296 | $2.00 / $12.00 |
| 21 | Gemini 3 ProGoogle | 95% interval 1482 to 1489Its interval overlaps 8 models above it | 41,829 | No list price |
| 22 | GPT-5.6 SolOpenAI · GPT-5.6 Sol (xHigh) | 95% interval 1481 to 1489Its interval overlaps 9 models above it | 43,994 | $4.00 / $20.00 |
| 23 | Qwen3.8 MaxAlibaba · Qwen3.8-Max | 95% interval 1479 to 1489Its interval overlaps 10 models above it | 36,324 | $2.00 / $6.00 |
| 24 | Kimi K3.1 ProMoonshot AI · Kimi K3.1 Pro (Max) · open weights | 95% interval 1472 to 1494Its interval overlaps 15 models above it | 3,443 | $2.00 / $10.00 |
| 25 | Gemini 3.6 Flash (High)Google | 95% interval 1478 to 1487Its interval overlaps 11 models above it | 35,405 | No list price |
| 26 | GLM-5.3Z.ai · GLM-5.3 (Max) · open weights | 95% interval 1478 to 1487Its interval overlaps 12 models above it | 31,017 | $1.40 / $4.40 |
| 27 | GPT-6.1 SolOpenAI · GPT-6.1 Sol (Max)Run GPT-6.1 Sol up to 75% below list priceCertified genuine by AIGROW on 11 November 2026 | 95% interval 1476 to 1488Its interval overlaps 14 models above it | 12,952 | |
| 28 | Claude Opus 4.8 (High)Anthropic | 95% interval 1478 to 1486Its interval overlaps 12 models above it | 63,128 | No list price |
| 29 | GPT-5.5OpenAI · GPT-5.5 (High) | 95% interval 1478 to 1485Its interval overlaps 13 models above it | 68,359 | $5.00 / $30.00 |
| 30 | MiMo-V2.6-ProXiaomi · open weights | 95% interval 1471 to 1490Its interval overlaps 17 models above it | 4,066 | No list price |
| 31 | Gemini 3.5 Flash (High)Google | 95% interval 1475 to 1482Its interval overlaps 10 models above it | 47,642 | No list price |
| 32 | Gemini 3.5 Flash (Medium)Google | 95% interval 1472 to 1480Its interval overlaps 9 models above it | 46,377 | No list price |
| 33 | GPT-5.5OpenAI | 95% interval 1472 to 1480Its interval overlaps 10 models above it | 69,937 | $5.00 / $30.00 |
| 34 | GPT-5.2 Chat (20260210)OpenAI | 95% interval 1472 to 1480Its interval overlaps 11 models above it | 35,708 | No list price |
| 35 | GPT-5.4 (High)OpenAI | 95% interval 1471 to 1479Its interval overlaps 11 models above it | 64,103 | No list price |
| 36 | GLM-5.2 (Max)Z.ai · open weights | 95% interval 1471 to 1479Its interval overlaps 12 models above it | 54,173 | No list price |
| 37 | DeepSeek V4.1 FlashDeepSeek · DeepSeek-V4.1-Flash-20260910 (Max) · open weights | 95% interval 1469 to 1481Its interval overlaps 15 models above it | 13,580 | $0.30 / $1.20 |
| 38 | Grok 4.20 Beta 1xAI | 95% interval 1470 to 1479Its interval overlaps 14 models above it | 27,690 | No list price |
| 39 | Claude Opus 4.8Anthropic | 95% interval 1470 to 1478Its interval overlaps 15 models above it | 64,170 | No list price |
| 40 | GLM-5.3-FlashZ.ai · open weights | 95% interval 1470 to 1479Its interval overlaps 16 models above it | 50,189 | $0.15 / $0.50 |
| 41 | GPT-6 AstraOpenAI · GPT-6 Astra (Max)Run GPT-6 Astra up to 75% below list priceCertified genuine by AIGROW on 11 November 2026 | 95% interval 1469 to 1480Its interval overlaps 18 models above it | 18,315 | |
| 42 | Qwen3.7-Max-PreviewAlibaba | 95% interval 1464 to 1484Its interval overlaps 23 models above it | 3,904 | No list price |
| 43 | Claude Opus 4.5 (High, 32K, 20251101)Anthropic | 95% interval 1470 to 1478Its interval overlaps 15 models above it | 37,253 | No list price |
| 44 | GPT-5.5 InstantOpenAI | 95% interval 1468 to 1478Its interval overlaps 20 models above it | 26,865 | No list price |
| 45 | Gemini 3 FlashGoogle | 95% interval 1469 to 1477Its interval overlaps 17 models above it | 31,133 | No list price |
| 46 | Claude Sonnet 5.5Anthropic · Claude Sonnet 5.5 (xHigh)Run Claude Sonnet 5.5 up to 60% below list priceCertified genuine by AIGROW on 11 November 2026 | 95% interval 1466 to 1479Its interval overlaps 22 models above it | 13,821 | |
| 47 | Grok 4.20 Beta (Reasoning, 0309)xAI | 95% interval 1468 to 1476Its interval overlaps 19 models above it | 65,713 | No list price |
| 48 | Claude Sonnet 4.6Anthropic | 95% interval 1469 to 1476Its interval overlaps 19 models above it | 70,017 | No list price |
| 49 | Grok 4.20 Multi-Agent Beta (0309)xAI | 95% interval 1467 to 1475Its interval overlaps 20 models above it | 64,252 | No list price |
| 50 | Claude Opus 4.5 (20251101)Anthropic | 95% interval 1467 to 1473Its interval overlaps 20 models above it | 72,313 | No list price |
| Further down the board: the other models on our price list | ||||
| 51 | GPT-5.6 TerraOpenAI · GPT-5.6 Terra (xHigh) | 95% interval 1464 to 1472Its interval overlaps 19 models above it | 48,825 | $2.00 / $12.00 |
| 59 | DeepSeek V4 ProDeepSeek · DeepSeek-V4-Pro (High, 20260813) · open weights | 95% interval 1457 to 1471Its interval overlaps 23 models above it | 9,584 | $1.32 / $3.96 |
| 60 | Claude Sonnet 5Anthropic · Claude Sonnet 5 (High) | 95% interval 1457 to 1465Its interval overlaps 10 models above it | 53,013 | $2.00 / $10.00 |
| 61 | Kimi K2.6Moonshot AI · open weights | 95% interval 1456 to 1465Its interval overlaps 11 models above it | 39,573 | $0.95 / $4.00 |
| 67 | GPT-6 SolOpenAI · GPT-6 Sol (Max) | 95% interval 1451 to 1462Its interval overlaps 13 models above it | 19,890 | $2.00 / $10.00 |
| 72 | Qwen3.7 PlusAlibaba · Qwen3.7-Plus | 95% interval 1451 to 1460Its interval overlaps 13 models above it | 41,318 | $0.40 / $1.60 |
| 75 | Gemini 3.5 Flash-LiteGoogle | 95% interval 1450 to 1459Its interval overlaps 16 models above it | 35,114 | $0.30 / $2.50 |
| 77 | GPT-5.6 LunaOpenAI · GPT-5.6 Luna (xHigh) | 95% interval 1449 to 1458Its interval overlaps 18 models above it | 40,641 | $0.20 / $1.20 |
| 78 | Gemma 4 31BGoogle · open weights | 95% interval 1444 to 1459Its interval overlaps 19 models above it | 6,130 | No list price |
| 87 | GPT-5.4 miniOpenAI · GPT-5.4 mini (High) | 95% interval 1444 to 1451Its interval overlaps 14 models above it | 62,795 | $0.75 / $4.50 |
| 94 | Grok 4.7xAI · Grok 4.7 (xHigh)Run Grok 4.7 up to 75% below list priceCertified genuine by AIGROW on 11 November 2026 | 95% interval 1437 to 1447Its interval overlaps 16 models above it | 21,586 | |
| 95 | Grok 4.3xAI | 95% interval 1438 to 1445Its interval overlaps 14 models above it | 70,242 | $1.25 / $2.50 |
| 98 | GPT-6 LunaOpenAI · GPT-6 Luna (Max) | 95% interval 1437 to 1445Its interval overlaps 16 models above it | 107,021 | $0.10 / $0.50 |
| 104 | MiniMax M3MiniMax · MiniMax-M3 · open weights | 95% interval 1432 to 1440Its interval overlaps 13 models above it | 72,963 | $0.30 / $1.20 |
| 112 | Qwen3.8 27BAlibaba · Qwen3.8-27B · open weights | 95% interval 1429 to 1438Its interval overlaps 16 models above it | 32,659 | $0.50 / $3.00 |
| 113 | Gemini 3.1 Flash-LiteGoogle · Gemini 3.1 Flash-Lite Preview | 95% interval 1429 to 1437Its interval overlaps 16 models above it | 63,629 | $0.25 / $1.50 |
| 121 | Mistral Medium 3.5Mistral AI · open weights | 95% interval 1420 to 1433Its interval overlaps 19 models above it | 11,656 | $1.50 / $7.50 |
| 126 | Muse Glimmer 30BMeta · Muse Glimmer · open weights | 95% interval 1415 to 1435Its interval overlaps 25 models above it | 3,793 | No list price |
| 129 | Mistral Large 4Mistral AI · open weights | 95% interval 1414 to 1432Its interval overlaps 25 models above it | 5,742 | $0.70 / $2.10 |
| 131 | Claude Haiku 5.5Anthropic · Claude Haiku 5.5 (High) | 95% interval 1416 to 1429Its interval overlaps 19 models above it | 13,239 | $0.10 / $0.50 |
| 166 | GPT-5.4 nanoOpenAI · GPT-5.4 nano (High) | 95% interval 1397 to 1405Its interval overlaps 10 models above it | 61,636 | $0.20 / $1.25 |
| 220 | gpt-oss-120bOpenAI · open weights | 95% interval 1347 to 1356Its interval overlaps 8 models above it | 30,133 | No list price |
| 254 | Llama 4 MaverickMeta · Llama 4 Maverick 17B 128E Instruct · open weights | 95% interval 1323 to 1331Its interval overlaps 11 models above it | 39,397 | No list price |
Worth paying for: the models no cheaper one beats
The models with an API price that no cheaper model outscores on this board, cheapest first. Every other priced model costs more than one of these and scores no higher. The price weighs input and output 3 to 1, the usual mix of a chat or document task.
| Model | Score | Rank | Per 1M tokens, 3:1 |
|---|---|---|---|
| GPT-6 LunaOpenAI · GPT-6 Luna (Max) | 1441 | 98 of 421 | |
| GLM-5.3-FlashZ.ai · open weights | 1474 | 40 of 421 | |
| DeepSeek V4.1 FlashDeepSeek · DeepSeek-V4.1-Flash-20260910 (Max) · open weights | 1475 | 37 of 421 | |
| Gemini 3.8 FlashGoogle · Gemini 3.8 Flash (High) | 1498 | 9 of 421 | |
| Gemini 4 CarbonGoogle · Gemini 4 Carbon (High) | 1526 | 1 of 421 |
Where the ranking comes from
The scores and intervals are LMArena’s. The numbering and the prices are ours.
- Blind votes
- LMArena puts the same prompt to two anonymous models and asks the person who wrote it to pick the better answer. The votes place every model on one scale, where a gap of 100 points means the higher model wins about 64 times in 100.
- Style control
- The scores discount answer length and formatting, so a model does not climb by writing more or by adding headings and lists.
- Numbers and ties
- Rows are numbered 1 to N by score, and no number is shared. Where a model’s 95% interval overlaps those of models above it, the votes cannot separate them, and the row says how many.
- Votes and measured results
- Blind votes show which answers people prefer, which mixes skill with taste in length, tone and layout. The main leaderboard ranks models by measured results on tests; these boards sit beside it as one aspect.
- Settings
- A model can appear more than once, at different reasoning settings: the line under its name gives the entry as LMArena lists it. Entries with web search switched on are a different product and carry no price.
- Prices
- The list price per million tokens from the maker’s own pricing page, read on 12 November 2026. It is a price per token, not per answer: a higher reasoning setting spends more tokens on the same question. Where AIGROW API credit sells a model, the list price is struck through and the price through the credit sits under it.
Source: LMArena, leaderboard dataset (revision 4217986c, published 9 November 2026), licensed under CC BY 4.0. We change no score: we add the prices and the links to our model pages.
What each of them costs to run
The price list works three everyday jobs on every model, and our own benchmark runs them on real business tasks to see which pass.
Scores published 9 November 2026