Who ranks #1 on the Science leaderboard?
As of August 21, 2026, GPT-5.6 Sol by OpenAI ranks #1 on GPQA at 94.6%. API pricing is $5.00/M input and $30.00/M output.
Science
🏆 LeaderboardAs of August 21, 2026, GPT-5.6 Sol is #1 for research and science at 94.6%. Ranked by GPQA: graduate-level science questions that resist simple search. Best AI for research and science, ranked by GPQA Diamond, HealthBench, SciCode, and FrontierMath. Compare research scores next to API price.
Updated August 21, 2026282 models33 providers
 GPT-5.6 Sol OpenAI · Proprietary | 94.6% | 82.8% | 56.9% | 32.3% | 44.0% | 85.2% | 83% | 89% | — | — | — | 57% | $35.00 |
 Claude Mythos Preview Anthropic · Proprietary | 94.6% | — | — | — | — | — | — | — | — | 93.2% | — | — | $60.00 |
Claude Mythos 5 Anthropic · Proprietary | 94.6% | 94.6% | — | — | — | — | — | — | — | — | — | — | $60.00 |
 Gemini 3.1 Pro Google · Proprietary | 94.3% | 94.4% | 59% | 17.7% | 59.1% | 76.1% | 80.5% | 36.9% | 96.4% | — | 16.7% | — | $17.50 |
Claude Opus 4.7 Anthropic · Proprietary | 94.2% | 86.4% | 54.5% | 12% | 54.9% | 83.0% | — | 43.8% | — | 91% | 22.9% | — | $30.00 |
GPT-5.5 OpenAI · Proprietary | 93.6% | 77.3% | 56.1% | 27.1% | 49.1% | 86.9% | 83.2% | 35.4% | — | — | 35.4% | — | $35.00 |
Claude Opus 4.8 Anthropic · Proprietary | 93.6% | 85.3% | 53.5% | 20.9% | 53.2% | 85.8% | — | 47.2% | — | 89.9% | 31.3% | — | $30.00 |
 Kimi K3OSS Moonshot AI · Open Source | 93.5% | 93.5% | 58.7% | 23.4% | 48.9% | 88.0% | 81.6% | — | — | 91.3% | — | — | $18.00 |
GPT-5.2 Pro OpenAI · Proprietary | 93.2% | — | — | — | — | — | — | — | — | — | — | — | $189.00 |
 Grok 4.5 xAI · Proprietary | 93% | 93.4% | 54.0% | 15.4% | 43.3% | 86.9% | — | — | — | — | — | — | $8.00 |
GPT-5.6 Terra OpenAI · Proprietary | 92.9% | 77.3% | 53.9% | 30% | 43.4% | 82.9% | 80.7% | 84.9% | — | — | — | 57% | $14.00 |
GPT-5.4 OpenAI · Proprietary | 92.8% | 89.4% | 56.6% | 23.4% | 41.3% | 77.5% | 81.2% | 47.6% | 96.1% | — | 27.1% | — | $17.50 |
 Qwen3.8 MaxOSS Qwen · Open Source | 92.6% | 92.7% | — | — | 40.7% | 85.0% | 82.3% | — | — | — | — | 60.2% | $8.00 |
Qwen3.7 Max Qwen · Proprietary | 92.4% | 90.9% | 53.5% | 11.4% | 38.8% | 79.4% | — | — | — | — | — | — | $5.00 |
GPT-5.2 OpenAI · Proprietary | 92.4% | 73.2% | — | — | 49.8% | 84.4% | 79.5% | 40.3% | 94.1% | 82.1% | 18.8% | — | $15.75 |
GPT-5.6 Luna OpenAI · Proprietary | 92.3% | 63.6% | 52.5% | 20.6% | 42.4% | 84.4% | 78.4% | 78.6% | — | — | — | 55.8% | $1.40 |
Gemini 3 Pro Google · Proprietary | 91.9% | 91.9% | — | 6.9% | 52.2% | 72.0% | 81% | 37.6% | 96.0% | 81.4% | 18.8% | — | $14.00 |
Claude Opus 4.6 Anthropic · Proprietary | 91.3% | 88.4% | — | — | 48.2% | 86.7% | 77.3% | 40.7% | — | 77.4% | 22.9% | — | $30.00 |
 GLM-5.2OSS Z AI · Open Source | 91.2% | 71.2% | 50.5% | 16.7% | 40.8% | 83.5% | — | — | — | — | — | — | $5.80 |
Kimi K2.6OSS Moonshot AI · Open Source | 90.5% | 90.8% | 52.2% | 8% | 40.1% | 78.2% | 80.1% | 39.0% | — | 86.7% | 14.6% | — | $4.93 |
Qwen3.6 Plus Qwen · Proprietary | 90.4% | 88.4% | 40.7% | 2.9% | 36.9% | 77.0% | 78.8% | 26.2% | — | 81.5% | 8.3% | — | $3.50 |
 Hy3OSS Tencent · Open Source | 90.4% | — | — | — | — | — | — | — | — | — | — | — | $0.66 |
Gemini 3 Flash Google · Proprietary | 90.4% | 89.4% | — | — | 55.9% | 69.9% | 81.2% | 35.6% | 95.8% | 80.3% | 4.2% | — | $3.50 |
Qwen3.7-Plus Qwen · Proprietary | 90.3% | 87.9% | 51.3% | 6% | — | — | 79% | — | — | 85.9% | — | — | $1.60 |
 DeepSeek-V4-Pro-MaxOSS DeepSeek · Open Source | 90.1% | 89.7% | 50% | 12.9% | — | — | — | — | — | — | — | — | $5.22 |
Claude Sonnet 4.6 Anthropic · Proprietary | 89.9% | 78.8% | 46.8% | 3.1% | — | — | 75.6% | 32.4% | 92.1% | — | 8.3% | — | $18.00 |
 Inkling-SmallOSS Thinking Machines · Open Source · via Thinking Machines Lab | 89.5% | 88.5% | 48.7% | 8.3% | 37.9% | 84.1% | 74% | — | — | 77.4% | — | — | $1.50 |
Qwen3.8-27BOSS Qwen · Open Source | 89.2% | — | — | — | — | — | — | — | — | 90.2% | — | — | $3.65 |
 Solar Pro 4 Upstage · Proprietary | 89% | — | — | — | — | — | — | — | — | — | — | — | $1.50 |
 Seed 2.0 Pro ByteDance · Proprietary | 88.9% | — | — | — | — | — | — | — | — | — | — | — | $3.50 |
Qwen3.5-397B-A17BOSS Qwen · Open Source | 88.4% | 85.9% | — | — | — | — | — | — | — | — | — | — | $4.20 |
GPT-5.1 Thinking OpenAI · Proprietary | 88.1% | — | — | — | — | — | — | 26.7% | — | — | — | — | $11.25 |
GPT-5.1 Instant OpenAI · Proprietary | 88.1% | — | — | — | — | — | — | 26.7% | — | — | — | — | $11.25 |
GPT-5.1 High OpenAI · Proprietary | 88.1% | — | 43.3% | 4.9% | — | — | — | — | — | — | — | — | $11.25 |
GPT-5.1 OpenAI · Proprietary | 88.1% | 66.7% | 43.3% | 4.9% | 52.7% | 88.1% | — | 26.7% | 96.4% | — | 4.2% | — | $11.25 |
GPT-5 Medium OpenAI · Proprietary | 88.1% | — | — | — | — | — | — | — | — | — | — | — | $11.25 |
DeepSeek-V4-Flash-MaxOSS DeepSeek · Open Source | 88.1% | — | 44.9% | 7.1% | — | — | — | — | — | — | — | — | $0.42 |
GPT-5.4 mini OpenAI · Proprietary | 88% | 88% | 49.9% | 10% | — | — | 76.6% | 28.3% | — | — | 2.1% | — | $5.25 |
Qwen3.6-27BOSS Qwen · Open Source | 87.8% | 85.9% | — | — | — | — | 75.8% | — | — | 78.4% | — | — | $4.20 |
GPT-5.3 Codex OpenAI · Proprietary | 87.7% | 87.7% | — | — | — | — | — | — | — | — | — | — | $15.75 |
Kimi K2.5OSS Moonshot AI · Open Source | 87.6% | — | 48.7% | 3.1% | — | — | 78.5% | — | — | 77.5% | — | — | $3.68 |
Grok-4 xAI · Proprietary | 87.5% | 87.5% | — | — | — | — | — | — | — | — | — | — | $18.00 |
DeepSeek-V4-Flash-0423OSS DeepSeek · Open Source | 87.4% | — | — | — | — | — | — | — | — | — | — | — | $0.30 |
GPT-5 High OpenAI · Proprietary | 87.3% | — | 42.9% | — | — | — | — | — | — | — | — | — | $11.25 |
 Nemotron 3 Ultra (550B A55B)OSS NVIDIA · Open Source · via OpenRouter | 87% | 86.1% | 44.6% | 3.1% | 38.6% | — | — | — | — | — | — | — | $2.70 |
Claude Opus 4.5 Anthropic · Proprietary | 87% | 85.5% | — | — | 45.2% | 83.3% | — | 20.7% | 93.2% | — | 4.2% | — | $30.00 |
Gemini 3.1 Flash-Lite Google · Proprietary | 86.9% | 81.8% | 41.9% | 1.1% | 47.6% | 63.9% | 76.8% | — | — | 73.2% | — | — | $1.75 |
Qwen3.5-122B-A10BOSS Qwen · Open Source | 86.6% | — | — | — | — | — | 76.9% | — | — | 77.2% | — | — | $3.60 |
Gemini 2.5 Pro Preview 06-05 Google · Proprietary | 86.4% | 84.8% | — | — | — | — | — | 10.3% | — | — | 2.1% | — | $11.25 |
GLM-5.1OSS Z AI · Open Source | 86.2% | 89.9% | 43.8% | 4.6% | 41.6% | 72.3% | — | 33.5% | — | — | 12.5% | — | $5.80 |
Showing 1–50 of 282 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
282 models across 33 providers. Search or jump to a lab — every model page stays linked here.
OpenAI
51 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 nanoo3-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 FlashGemini 3.5 FlashGemma 4 26B-A4BGemma 4 31BGemini 3.1 Flash-LiteGemini 3.1 ProGemini 3 FlashGemini 3 ProGemma 3n E4B InstructedGemini 2.5 Flash-LiteGemini 2.5 Pro Preview 06-05Gemini 2.5 FlashGemini 2.5 ProGemma 3 12BGemma 3 27BGemma 3 4BGemini 2.0 Flash-LiteGemini 2.0 FlashGemma 2 27BGemini 1.5 FlashGemini 1.5 ProGemini 1.5 Flash 8BGemini 1.0 Pro
Cursor
2 modelsxAI
15 modelsDeepSeek
16 modelsQwen
38 modelsQwen3.8-27BQwen3.8-2.4T-A95BQwen3.8 MaxQwen3.7 FlashQwen3.7-PlusQwen3.7 MaxQwen3.6-27BQwen3.6-35B-A3BQwen3.6 PlusQwen3.5-9BQwen3.5-122B-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 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 32BQwen3-Coder 480B A35B InstructQwen2.5 VL 72B InstructQwen3-CoderQwQ-32B-PreviewQwen2.5 72B InstructQwen2.5 7B InstructQwen2.5-Coder 32B Instruct
AI21 Labs
2 models
Amazon
5 models
Baidu
1 modelsByteDance
2 models
Cohere
3 models
IBM
1 models
Inception
1 models
inclusionAI
1 models
LG AI Research
1 models
Meituan
4 models
Meta
12 models
Mistral
23 modelsMistral 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 MediumMistral Small 3.1 24B BaseMistral Small 3.1 24B InstructMistral Small 3 24B InstructPixtral LargeMinistral 8B InstructMistral SmallPixtral-12BMistral Large 2Mistral NeMo Instruct
Moonshot AI
9 models
Nous Research
1 modelsNVIDIA
5 models
Poolside
2 models
Sakana AI
1 models
StepFun
1 modelsTencent
1 modelsThinking Machines
1 models
Unisound
1 modelsUpstage
1 models
Xiaomi
3 modelsWhat is the best AI for research?
As of August 21, 2026, GPT-5.6 Sol by OpenAI is #1 for research and science at 94.6%. Ranked by GPQA: graduate-level science questions that resist simple search. This board also tracks GPQA, GPQA Diamond, SciCode, CritPt. Next on the same board: Claude Mythos 5 and Claude Mythos Preview. Related leaders: Gemini 3.7 Flash on GPQA Diamond at 94.8%; Claude Fable 5 on SciCode at 60.2%. This science leaderboard ranks models by GPQA. Scores come from public evals. Prices are the live API rates in the table above.
Sources: GPQA (GitHub) (https://github.com/idavidrein/gpqa); 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 | GPQA | Input /M | Output /M |
|---|---|---|---|---|
| 1 | GPT-5.6 Sol | 94.6% | $5.00 | $30.00 |
| 2 | Claude Mythos 5 | 94.6% | $10.00 | $50.00 |
| 3 | Claude Mythos Preview | 94.6% | $10.00 | $50.00 |
| 4 | Gemini 3.1 Pro | 94.3% | $2.50 | $15.00 |
| 5 | Claude Opus 4.7 | 94.2% | $5.00 | $25.00 |
| 6 | Claude Opus 4.8 | 93.6% | $5.00 | $25.00 |
| 7 | GPT-5.5 | 93.6% | $5.00 | $30.00 |
| 8 | Kimi K3 | 93.5% | $3.00 | $15.00 |
What is the best AI for research?
People search best AI for research more than best AI for science. This board uses GPQA Diamond for graduate science, SciCode for scientific programming, HealthBench for medical dialogue, and chart evals for papers with figures. Deep-research products are agents on top of a model. Rank the model here.
What is HealthBench?
HealthBench scores how a model handles health conversations. It is closer to a clinician chat than to GPQA. If your product is medical, sort HealthBench. If your product is physics QA, sort GPQA Diamond.
Related LLM leaderboards
Individual benchmark pages
Rank one eval at a time. All LLM benchmarks.
Science FAQ
What is the best AI for research?
As of August 21, 2026, GPT-5.6 Sol by OpenAI is #1 for research and science at 94.6%. Ranked by GPQA: graduate-level science questions that resist simple search. This board also tracks GPQA, GPQA Diamond, SciCode, CritPt. Next on the same board: Claude Mythos 5 and Claude Mythos Preview. Related leaders: Gemini 3.7 Flash on GPQA Diamond at 94.8%; Claude Fable 5 on SciCode at 60.2%.
What are the top models on GPQA?
The current GPQA ranking as of August 21, 2026 is 1. GPT-5.6 Sol at 94.6%; 2. Claude Mythos 5 at 94.6%; 3. Claude Mythos Preview at 94.6%.
Which science model is the cheapest?
Llama 3.2 3B Instruct is the cheapest scored model on this science leaderboard at $0.01/M input and $0.02/M output ($0.03 blended). GPT-5.6 Sol still leads GPQA at 94.6%.
Should I always pick the #1 GPQA model?
Not automatically. GPT-5.6 Sol leads GPQA, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh GPQA against input/output price, context window, and related evals.
How often is the Science leaderboard updated?
Scores and API prices on this page are refreshed from published evals and provider rates. The snapshot is labeled August 21, 2026. Treat it as a current index, not a one-off blog post.
What is the best LLM for research?
GPQA Diamond and FrontierMath rank scientific reasoning. SciCode ranks scientific programming. HealthBench ranks medical dialogue.
What is HealthBench?
HealthBench is OpenAI's medical conversation eval. It scores how models handle clinical questions, not just multiple-choice science.
Can I compare science scores with API cost?
Yes. This page keeps the science evals next to input and output prices so a lab model can be judged on both accuracy and spend.
What is the best AI for science?
Best AI for science on this page means GPQA Diamond, Frontier Science, SciCode, HealthBench, and chart/vision science evals, next to API price. Best AI for research is the higher-volume version of the same question.
Can I use this ranking for medical research?
Use HealthBench and MedQA as a public signal, then run your own eval. This is not clinical advice and it is not a device. Token price still matters if you screen a lot of papers.