Best Google Reasoning Models
The best Google model for reasoning is Gemini 3.5 Flash — 50.2 intelligence with extended step-by-step thinking. Gemini 3.5 Flash (batch) (50.2) and Gemini 3.6 Flash (50.1) round out the top three.
Large language models with extended reasoning / thinking, ranked by intelligence. The smartest AI models for complex multi-step reasoning, math and analysis.
- 1
gemini-3.5-flashReasoningToolsJSON+250.2 intel · $1.50/M · 1.0M ctx50.2Intelligence - 2gemini-3.5-flash:batchReasoningToolsJSON+250.2 intel · $0.750/M · 1.0M ctx50.2Intelligence
- 3gemini-3.6-flashReasoningToolsJSON+250.1 intel · $1.50/M · 1.0M ctx50.1Intelligence
- 4gemini-3.6-flash:batchReasoningToolsJSON+250.1 intel · $0.750/M · 1.0M ctx50.1Intelligence
- 5gemini-3.1-pro-previewReasoningToolsJSON+246.5 intel · $2.00/M · 1.0M ctx46.5Intelligence
- 6gemini-3.1-pro-preview:batchReasoningToolsJSON+246.5 intel · $1.00/M · 1.0M ctx46.5Intelligence
- 7gemini-3.5-flash-liteReasoningToolsJSON+236.5 intel · $0.300/M · 1.0M ctx36.5Intelligence
- 8gemini-3.5-flash-lite:batchReasoningToolsJSON+236.5 intel · $0.150/M · 1.0M ctx36.5Intelligence
- 9gemini-2.5-proReasoningToolsJSON+225.8 intel · $1.25/M · 1.0M ctx25.8Intelligence
- 10gemini-2.5-pro:batchReasoningToolsJSON+225.8 intel · $0.625/M · 1.0M ctx25.8Intelligence
- 11gemini-3.1-flash-liteReasoningToolsJSON+225.0 intel · $0.250/M · 1.0M ctx25.0Intelligence
- 12gemini-3.1-flash-lite:batchReasoningToolsJSON+225.0 intel · $0.125/M · 1.0M ctx25.0Intelligence
- 13gemini-3.1-flash-lite-previewReasoningToolsJSON+225.0 intel · $0.250/M · 1.0M ctx25.0Intelligence
- 14gemini-2.5-flashReasoningToolsJSON+214.1 intel · $0.300/M · 1.0M ctx14.1Intelligence
- 15gemini-2.5-flash:batchReasoningToolsJSON+214.1 intel · $0.150/M · 1.0M ctx14.1Intelligence
- 16gemini-2.5-flash-liteReasoningToolsJSON+26.9 intel · $0.100/M · 1.0M ctx6.9Intelligence
- 17gemini-2.5-flash-lite:batchReasoningToolsJSON+26.9 intel · $0.050/M · 1.0M ctx6.9Intelligence
- 18gemini-3.1-flash-lite-imageReasoningJSONVision+1$0.250/M · 66K ctx—Intelligence
- 19gemini-3.1-flash-imageReasoningJSONVision+1$0.500/M · 131K ctx—Intelligence
- 20gemini-3-pro-imageReasoningToolsJSON+2$2.00/M · 131K ctx—Intelligence
- 21gemma-4-26b-a4b-itReasoningToolsJSON+1$0.070/M · 262K ctx—Intelligence
- 22gemma-4-26b-a4b-it:freeReasoningToolsJSON+1Free/M · 262K ctx—Intelligence
- 23gemma-4-31b-itReasoningToolsJSON+1$0.100/M · 262K ctx—Intelligence
- 24gemma-4-31b-it:freeReasoningToolsJSON+1Free/M · 262K ctx—Intelligence
- 25gemini-3.1-flash-image-previewReasoningJSONVision+1$0.500/M · 66K ctx—Intelligence
Frequently asked
What is the best Google model for reasoning?
The best Google model for reasoning is Gemini 3.5 Flash — 50.2 intelligence with extended step-by-step thinking. Gemini 3.5 Flash (batch) (50.2) and Gemini 3.6 Flash (50.1) round out the top three.
What's a good alternative to Gemini 3.5 Flash?
Gemini 3.5 Flash (batch) (50.2) is the closest alternative on this metric, followed by Gemini 3.6 Flash (50.1). See the full ranking above for the tradeoffs.
How many Google models are there?
modelgrep tracks 39 Google models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Gemini 3.5 Flash. 25 of them qualify for this ranking.