> Gemini 3.1 Pro is a closed AI model from Google, released 19 Feb 2026. Index score 166 (GPT-4 = 100), rank 29 of 229 ranked models. API price $2.0 in / $12 out per million tokens, 1.05M context. [Models](https://themodelindex.org/models/) /[Google](https://themodelindex.org/labs/google/) # Gemini 3.1 Pro Google Released 19 Feb 2026 Closed Flagship Date verified [Compare](https://themodelindex.org/compare/gemini-3-1-pro-vs-kimi-k2-5/) [Announcement](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-pro/) 166155–177 Index score #29 of 229 models 8/ 8 Core tests taken 6 of 6 areas · plus 22 anchor tests −4 Versus the frontier at release best then: GPT-5.3-Codex $2.0/ $12 Price per million tokens input / output, list price 1.05M Context window tokens it reads at once ## Where it sits · on the frontier _Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_ Among the first models to reach this score. ## Test results · by area · tick = best by any model Show 15 anchor tests Reasoning & knowledge evidence GPQA Diamond 94% Humanity's Last Exam 46% Maths evidence FrontierMath T1-3 60% Coding evidence SWE-bench Verified 76% Terminal-Bench 80% Agents evidence APEX-Agents 35% Novel problems evidence ARC-AGI-2 77% Long tasks evidence METR time horizon 6.4 h Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above. ## What others say · rank on each leaderboard The Model Index independent tests, our method #29 of 219 · 166 LMArena · Creative writing creative writing #11 of 386 · 1480 LMArena · Text overall chat quality, judged by people #17 of 388 · 1487 LMArena · Maths maths questions in chat #26 of 373 · 1488 LMArena · Coding coding questions in chat #32 of 383 · 1521 Epoch Capabilities Index overall capability from many benchmarks #30 of 239 · 154.8 Artificial Analysis Intelligence Index overall capability across ten evaluations #30 of 207 · 30 LMArena · Vision understanding images #23 of 149 · 1280 LiveBench · Overall overall, with fresh questions to limit contamination #22 of 58 · 77 LMArena · WebDev building web apps and front ends #61 of 123 · 1446 LMArena · Documents working with long documents #29 of 41 · 1444 Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source. ## Best at · top three among current models 1st SWE-bench Verified Epoch AI · independent 1st Terminal-Bench Epoch AI · independent 1st METR time horizon Epoch AI · independent 2nd instruction following questions LiveBench · Instruction Following 3rd Humanity's Last Exam Epoch AI · independent Where this model places in the top three of today's models, on category leaderboards and on our core tests. ## Where to use it · prices checked 1 Oct 2026 #### From the lab Gemini app · subscription ↗ Google AI Studio API ↗ #### API providers · 2 · per million tokens, in / out G Google $3.6 / $21.6 cheapest G Google AI Studio $3.6 / $21.6 ↗ Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps. ## Facts and sources Released 19 Feb 2026 Announcement [blog.google ↗](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-pro/) Release entry Gemini 3.1 Pro Scored as Gemini 3.1 Pro Artificial Analysis index 30 Output speed 113 tokens/s Hugging Face closed weights ## Google releases · around this one Gemini 3 Pro Closed 18 NOV 2025 index 161 Gemini 3 Flash Closed 17 DEC 2025 index 158 Gemini 3.1 Pro Closed 19 FEB 2026 index 166 Gemini 3.1 Flash-Lite Closed 3 MAR 2026 index 141 Gemma 4 Open 2 APR 2026 index 138 --- Source: https://themodelindex.org/models/gemini-3-1-pro/ · The Model Index · data as of 2026-10-01