Best LLMs for Science — Google
The best Google model for science is Gemini 3.1 Pro Preview, scoring 94.1% on GPQA Diamond — graduate-level physics, chemistry and biology. Gemini 3.6 Flash (92.8%) and Gemini 3.5 Flash (92.2%) round out the top three.
- 1
gemini-3.1-pro-previewReasoningToolsJSON+246.5 intel · $2.00/M · 136 t/s94.1%GPQA - 2gemini-3.6-flashReasoningToolsJSON+250.1 intel · $1.50/M · 135 t/s92.8%GPQA
- 3gemini-3.5-flashReasoningToolsJSON+250.2 intel · $1.50/M · 275 t/s92.2%GPQA
- 4gemini-2.5-proReasoningToolsJSON+225.8 intel · $1.25/M · 85 t/s84.4%GPQA
- 5gemini-3.5-flash-liteReasoningToolsJSON+236.5 intel · $0.300/M · 160 t/s83.8%GPQA
- 6gemini-3.1-flash-liteReasoningToolsJSON+225.0 intel · $0.250/M · 337 t/s82.2%GPQA
- 7gemini-3.1-flash-lite-previewReasoningToolsJSON+225.0 intel · $0.250/M · 337 t/s82.2%GPQA
- 8gemini-2.5-flashReasoningToolsJSON+214.1 intel · $0.300/M · 150 t/s68.3%GPQA
- 9gemini-2.5-flash-liteReasoningToolsJSON+26.9 intel · $0.100/M · 107 t/s47.4%GPQA
How this is ranked
AI models ranked by GPQA Diamond — graduate-level physics, chemistry and biology questions written to be un-Googleable, so the score reflects reasoning from knowledge rather than retrieval. The best large language models for scientific research and hard-science work.
Frequently asked
What is the best Google model for science?
The best Google model for science is Gemini 3.1 Pro Preview, scoring 94.1% on GPQA Diamond — graduate-level physics, chemistry and biology. Gemini 3.6 Flash (92.8%) and Gemini 3.5 Flash (92.2%) round out the top three.
What's a good alternative to Gemini 3.1 Pro Preview?
Gemini 3.6 Flash (92.8%) is the closest alternative on this metric, followed by Gemini 3.5 Flash (92.2%). See the full ranking above for the tradeoffs.
How many Google models are there?
modelgrep tracks 30 Google models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Gemini 3.5 Flash. 9 of them qualify for this ranking.