Who ranks #1 on the HellaSwag leaderboard?
As of August 31, 2026, Claude 3 Opus by Anthropic ranks #1 on HellaSwag at 95.4%. API pricing is $15.00/M input and $75.00/M output.
HellaSwag
🏆 LeaderboardAs of August 31, 2026, Claude 3 Opus is #1 for HellaSwag at 95.4%. Ranked by HellaSwag, a sentence-completion quiz, not a writing sample. 29 models in this index have a published HellaSwag score. HellaSwag leaderboard with live API prices. Tests commonsense natural language inference — given a scenario, the model predicts the most likely continuation.
Updated August 31, 2026345 models36 providers
HellaSwag vs price
29 models. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price — a dot under it is a worse deal than something on the line.
Best score at each price#1 on this board
Showing 1–50 of 345 models
Next step
You found the model. Now ship the product.
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
The index
All Large Language Models
345 models across 36 providers. Search or jump to a lab — every model page stays linked here.
OpenAI
52 modelsGPT-5.6 CyberGPT-5.6 LunaGPT-5.6 SolGPT-5.6 TerraGPT-5.5 InstantGPT-5.5GPT-5.5 ProGPT-5.4 miniGPT-5.4 nanoGPT-5.4GPT-5.3 ChatGPT-5.3 CodexGPT-5.2 CodexGPT-5.2GPT-5.2 ProGPT-5.1 CodexGPT-5.1GPT-5.1 Codex HighGPT-5.1 Codex MiniGPT-5.1 HighGPT-5.1 InstantGPT-5.1 MediumGPT-5.1 ThinkingGPT-5 CodexGPT-5GPT-5 HighGPT-5 MediumGPT-5 miniGPT-5 nanoGPT OSS 120BGPT OSS 120B HighGPT OSS 20BGPT OSS 20B Higho3-proo3o4-miniGPT-4.1GPT-4.1 miniGPT-4.1 nanoGPT-4.5o3-minio1o1-proo1-minio1-previewGPT-4oGPT-4o miniChatGPT-4o LatestGPT-4oGPT-4 TurboGPT-4GPT-3.5 Turbo
Anthropic
22 modelsClaude Opus 5Claude Sonnet 5Claude Fable 5Claude Mythos 5Claude Opus 4.8Claude Opus 4.7Claude Sonnet 4.6Claude Opus 4.6Claude Opus 4.5Claude Haiku 4.5Claude Sonnet 4.5Claude Opus 4.1Claude Opus 4Claude Sonnet 4Claude 3.7 SonnetClaude 3.5 HaikuClaude 3.5 SonnetClaude 3.5 SonnetClaude 3 HaikuClaude 3 OpusClaude 3 SonnetClaude Mythos Preview
Gemini 3.7 FlashGemini 3.5 Flash-LiteGemini 3.6 FlashDiffusionGemma 26B-A4BGemma 4 12BGemini 3.5 FlashGemma 4 26B-A4BGemma 4 31BGemma 4 E2BGemma 4 E4BGemini 3.1 Flash-LiteGemini 3.1 ProGemini 3 FlashGemini 3 ProGemma 3n E2B InstructedGemma 3n E4B InstructedGemini 2.5 Flash-LiteGemini 2.5 Pro Preview 06-05Gemini 2.5 FlashGemini 2.5 ProGemini DiffusionMedGemma 4B ITGemma 3 12BGemma 3 1BGemma 3 27BGemma 3 4BGemini 2.0 Flash-LiteGemini 2.0 FlashGemma 2 27BGemma 2 9BGemini 1.5 FlashGemini 1.5 ProGemini 1.5 Flash 8BGemini 1.0 Pro
Cursor
2 models
xAI
17 models
DeepSeek
20 modelsDeepSeek-V4-Flash-Vision-ExpDeepSeek-V4-Pro-0813DeepSeek-V4-Flash-0731DeepSeek-V4-Flash-0423DeepSeek-V4-Flash-MaxDeepSeek-V4-Pro-MaxDeepSeek-V3.2DeepSeek-V3.2 (Non-thinking)DeepSeek-V3.2-ExpDeepSeek-R1-0528DeepSeek-V3 0324DeepSeek R1 Distill Llama 70BDeepSeek R1 Distill Qwen 32BDeepSeek-R1DeepSeek-V3.1DeepSeek-V3DeepSeek VL2DeepSeek VL2 SmallDeepSeek VL2 TinyDeepSeek-V2.5
Qwen
55 modelsQwen3.8 FlashQwen3.8-Flash-NextQwen3.8-27BQwen3.8-2.4T-A95BQwen3.8 MaxQwen3.7 FlashQwen3.7-PlusQwen3.7 MaxQwen3.6-27BQwen3.6-35B-A3BQwen3.6 PlusQwen3.5-0.8BQwen3.5-2BQwen3.5-4BQwen3.5-9BQwen3.5-122B-A10BQwen3.5-27BQwen3.5-35B-A3BQwen3.5-397B-A17BQwen3 MaxQwen3 VL 235B A22B InstructQwen3 VL 235B A22B ThinkingQwen3 VL 30B A3B InstructQwen3 VL 30B A3B ThinkingQwen3 VL 32B InstructQwen3 VL 32B ThinkingQwen3 VL 4B InstructQwen3 VL 4B ThinkingQwen3 VL 8B InstructQwen3 VL 8B ThinkingQwen3-Next-80B-A3B-InstructQwen3-Next-80B-A3B-ThinkingQwen3-235B-A22B-Thinking-2507Qwen3-235B-A22B-Instruct-2507Qwen3 235B A22BQwen3 30B A3BQwen3 32BQwen2.5-Omni-7BQwQ-32BQwen2.5 VL 32B InstructQwen3-Coder 480B A35B InstructQwen2.5 VL 72B InstructQwen2.5 VL 7B InstructQwen3-CoderQvQ-72B-PreviewQwQ-32B-PreviewQwen2.5 14B InstructQwen2.5 32B InstructQwen2.5 72B InstructQwen2.5 7B InstructQwen2.5-Coder 32B InstructQwen2.5-Coder 7B InstructQwen2-VL-72B-InstructQwen2 72B InstructQwen2 7B Instruct
AI21 Labs
2 models
ByteDance
4 models
Inception
1 models
inclusionAI
1 models
LG AI Research
1 models
Liquid AI
2 models
Meituan
4 models
Meta
12 models
Microsoft
9 models
Mistral
26 modelsShieldstral 1.0 (3B)Mistral Medium 3.5Mistral Small 4Min istral 3 (3B Reasoning 2512)MiniStral 3 (14B Instruct 2512)Ministral 3 (14B Reasoning 2512)Ministral 3 (3B Instruct 2512)Ministral 3 (8B Instruct 2512)Ministral 3 (8B Reasoning 2512)Mistral Large 3 (675B Instruct 2512)Mistral Large 3Devstral Small 1.1Devstral MediumMistral Small 3.2 24B InstructMagistral MediumMagistral Small 2506Mistral Small 3.1 24B BaseMistral Small 3.1 24B InstructMistral Small 3 24B InstructPixtral LargeMinistral 8B InstructMistral SmallPixtral-12BMistral Large 2Mistral NeMo InstructCodestral-22B
Moonshot AI
11 models
Nous Research
1 models
NVIDIA
9 models
OpenBMB
1 models
Poolside
2 models
Sakana AI
1 models
Sarvam AI
2 models
StepFun
2 models
Tencent
1 models
Thinking Machines
1 models
Unisound
1 models
Upstage
1 modelsWhich model leads HellaSwag right now?
As of August 31, 2026, Claude 3 Opus by Anthropic is #1 for HellaSwag at 95.4%. Ranked by HellaSwag, a sentence-completion quiz, not a writing sample. This board also tracks HellaSwag. Next on the same board: GPT-4 and GPT-4o. This hellaswag leaderboard ranks models by HellaSwag. Scores come from public evals. Prices are the live API rates in the table above.
Sources: OpenAI API pricing (https://developers.openai.com/api/docs/pricing); Anthropic Claude API pricing (https://platform.claude.com/docs/en/about-claude/pricing); Gemini API pricing (https://ai.google.dev/gemini-api/docs/pricing)
| Rank | Model | HellaSwag | Input /M | Output /M |
|---|---|---|---|---|
| 1 | Claude 3 Opus | 95.4% | $15.00 | $75.00 |
| 2 | GPT-4 | 95.3% | $30.00 | $60.00 |
| 3 | GPT-4o | 95% | $2.50 | $10.00 |
| 4 | Gemini 1.5 Pro | 93.3% | $2.50 | $10.00 |
| 5 | Gemini 2.5 Pro | 90.9% | $1.25 | $10.00 |
| 6 | MiMo-V2.5-Pro | 89.8% | $0.43 | $0.87 |
| 7 | Claude 3 Sonnet | 89% | $3.00 | $15.00 |
| 8 | DeepSeek-V3 | 88.9% | $0.27 | $1.10 |
Related LLM leaderboards
Individual benchmark pages
Rank one eval at a time. All LLM benchmarks.
HellaSwag FAQ
What are the top models on HellaSwag?
The current HellaSwag ranking as of August 31, 2026 is 1. Claude 3 Opus at 95.4%; 2. GPT-4 at 95.3%; 3. GPT-4o at 95%.
Which hellaswag model is the cheapest?
Llama 3.2 3B Instruct is the cheapest scored model on this hellaswag leaderboard at $0.01/M input and $0.02/M output ($0.03 blended). Claude 3 Opus still leads HellaSwag at 95.4%.
Should I always pick the #1 HellaSwag model?
Not automatically. Claude 3 Opus leads HellaSwag, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh HellaSwag against input/output price, context window, and related evals.
How often is the HellaSwag leaderboard updated?
Scores and API prices on this page are refreshed from published evals and provider rates. The snapshot is labeled August 31, 2026. Treat it as a current index, not a one-off blog post.
What is HellaSwag?
Tests commonsense natural language inference — given a scenario, the model predicts the most likely continuation. This page ranks models that have published a HellaSwag score, with live API token prices on the same row.
Where is the HellaSwag leaderboard?
This page is the HellaSwag leaderboard. Models are sorted by HellaSwag, with input and output token prices on the same row so you can weigh score against cost. Official boards often omit price; that comparison is the point of this index.
How is this HellaSwag ranking different from the official board?
Official eval pages own the methodology. This page keeps the published HellaSwag score next to live API $/M so you can pick a production SKU, not only a trophy number.