GoogleReasoning modelGemini 3 Pro
Gemini 3 Pro is a Google proprietary reasoning model, released 18 Nov 2025. Its best configuration ranks #101 of 756 on the BenchLeader Index at 60.8 ±3.4, in the upper half. The ± is the point: 180 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (68) and lowest in maths (54). It has been measured at 4 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 2 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Full answer
- –
- Cost per run
- –
- Released
- 18 Nov 2025
- Overall index61
- Reasoning66
- Coding58
- Agents & tools62
- Maths54
- Knowledge57
- Instruction following63
- Human preference68
- Multimodal66
Versions
Google has shipped 11 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Gemini 3.1 Pro | 5 Mar 2026 | 62.6 | #78 |
| Gemini 3 Prothis page | 18 Nov 2025 | 60.8 | #101 |
| Gemini 2.5 Pro | 25 Mar 2025 | 54.0 | #247 |
| Gemini 1.5 Pro | 15 Feb 2025 | 42.5 | #573 |
| Gemini 2.0 Pro | 5 Feb 2025 | 47.1 | #445 |
| Gemini 1.5 Pro 002 | 24 Sept 2024 | 44.7 | #507 |
| Gemini 1.5 Pro 001 | 14 May 2024 | 44.7 | #508 |
| Gemini 1.0 Pro 001 | 13 Dec 2023 | – | – |
| Gemini Pro | – | – | – |
| Gemini 1.0 Pro | – | – | – |
| Gemini 1.0 Pro 002 | – | – | – |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| low | 53.9 | #257 | – | – | $0.0044 | Agents & tools 63 · Composite 55 · Instruction following 51 · Knowledge 63 · Long context 62 · Reasoning 41 |
| high | 60.2 | #107 | – | – | $0.0044 | Agents & tools 59 · Coding 61 · Composite 62 · Instruction following 69 · Knowledge 63 · Long context 63 · Maths 63 · Multimodal 63 · Reasoning 57 |
| thinking | – | – | – | – | – | |
| not statedbest | 60.8 | #101 | – | – | – | Agents & tools 62 · Coding 58 · Human preference 68 · Instruction following 63 · Knowledge 57 · Maths 54 · Multimodal 66 · Reasoning 66 |
How its index has moved
8 Sept 2026 to 4 Oct 2026- not stated
- high
- low
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| GPQA Diamond | – | – | – | 92.6%#25 | Epoch AI Benchmarking Hub | |
| Humanity's Last Exam | – | – | – | 37.5%#7 | Scale AI / CAIS | |
| SimpleBench | – | – | – | 76.4%#7 | SimpleBench | |
| LMArena Hard Prompts | – | – | – | 1503#28 | LMArena | |
| GPQA Diamond (AA)not in index | 88.7%#84 | 90.8%#55 | – | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 29.5%#138 | 39.7%#81 | – | – | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | – | 91.7%#18 | – | – | Vals AI | |
| Kagi LLM Benchmark | – | – | – | 80.1%#9 | Kagi LLM Benchmark | |
| GPQA Diamond (HELM)not in index | – | – | – | 80.3%#1 | HELM Capabilities | |
| ARC-AGI-1 | – | – | – | 75.0%#112 | ARC Prize | |
| ARC-AGI-2 | – | – | – | 54.0%#88 | ARC Prize | |
| CritPt | 0.0%#293 | 9.1%#112 | – | – | Artificial Analysis | |
| SciPredictnot in index | – | – | – | 25.3%#1 | Scale AI SEAL | |
| Chess Puzzlesnot in index | – | – | – | 31.0%#48 | Epoch AI Benchmarking Hub | |
| CL-benchnot in index | – | – | – | 15.8%#17 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | – | – | – | 61.2%#14 | ForecastBench |
Coding
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| SWE-bench Verified (Epoch) | – | – | – | 72.9%#21 | Epoch AI Benchmarking Hub | |
| WeirdML | – | – | – | 69.9%#34 | WeirdML | |
| GSO-Bench | – | – | – | 18.6%#17 | GSO-Bench | |
| LMArena Coding | – | – | – | 1518#42 | LMArena | |
| LMArena WebDev | – | – | – | 1439#68 | LMArena | |
| LiveCodeBench | – | – | – | 86.4%#22 | Vals AI | |
| SWE-bench (Vals)not in index | – | 76.4%#35 | – | – | Vals AI | |
| SWE-Bench Pro | – | – | – | 43.3%#8 | Scale AI SEAL | |
| SWE-bench Verified (bash only) | – | 69.6%#13 | – | 74.2%#6 | SWE-bench | |
| SWE-bench Verified (any scaffold)not in index | – | – | – | 74.2%#6 | SWE-bench | |
| Vibe Code Bench v1.1not in index | – | 14.3%#78 | – | – | Vals AI | |
| SWE-Bench Pro (private)not in index | – | – | – | 43.3%#8 | Scale AI SEAL | |
| ALE-Benchnot in index | – | – | – | 1176.8#38 | Epoch AI Benchmarking Hub | |
| AlgoTunenot in index | – | – | – | 1.8#4 | AlgoTune |
Agents & tools
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | – | 69.4%#7 | Terminal-Bench | |
| GDPval | – | – | – | 40.3%#5 | OpenAI | |
| Remote Labor Index | – | – | – | 1.3%#14 | Scale AI / CAIS | |
| Terminal-Bench Hard | 34.1%#90 | 41.7%#50 | – | – | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 68.1%#161 | 87.1%#80 | – | – | Artificial Analysis | |
| MCP Atlas | – | – | – | 70.3%#20 | Scale AI SEAL | |
| BFCL Overall | – | – | – | 72.5%#3 | Berkeley Function Calling Leaderboard | |
| τ²-bench | – | 82.5%#5 | – | – | τ²-bench | |
| Poker Agentnot in index | – | – | – | 1078.9%#6 | Vals AI | |
| Terminal-Bench 2.0 (Vals)not in index | – | 55.1%#15 | – | – | Vals AI | |
| BALROGnot in index | – | – | – | 58.1%#4 | BALROG | |
| DeepResearch Benchnot in index | 46.3%#28 | – | – | – | DeepResearch Bench | |
| METR Time Horizonsnot in index | – | – | – | 71.0%#9 | METR | |
| Vending-Bench 2not in index | – | – | – | 5478.2#24 | Andon Labs |
Maths
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| OTIS Mock AIME | – | – | – | 91.4%#60 | Epoch AI Benchmarking Hub | |
| ProofBench | – | – | – | 20.0%#49 | Vals AI | |
| AIME (Vals) | – | 96.7%#4 | – | – | Vals AI | |
| MGSM | – | 93.9%#7 | – | – | Vals AI | |
| AIME 2026 | – | – | – | 91.7%#24 | MathArena | |
| HMMT February 2026 | – | – | – | 86.4%#20 | MathArena | |
| MathArena Apex | – | – | – | 23.4%#14 | MathArena | |
| Omni-MATH (HELM) | – | – | – | 55.6%#13 | HELM Capabilities | |
| MATH 500not in index | – | 96.4%#1 | – | – | Vals AI | |
| LMArena Maths | – | – | – | 1477#39 | LMArena |
Knowledge
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| AA-Omniscience | 1.8#110 | 15.3#76 | – | – | Artificial Analysis | |
| MMLU-Pro | – | – | – | 90.1%#7 | Vals AI | |
| LegalBench | – | 87.0%#6 | – | – | Vals AI | |
| CorpFin | – | 63.7%#42 | – | – | Vals AI | |
| TaxEval | – | 72.6%#60 | – | – | Vals AI | |
| MedQA | – | 96.0%#8 | – | – | Vals AI | |
| PRBench Finance | – | – | – | 39.2%#25 | Scale AI SEAL | |
| PRBench Legal | – | – | – | 40.6%#27 | Scale AI SEAL | |
| MultiNRC | – | – | – | 59.0%#6 | Scale AI SEAL | |
| MMLU-Pro (HELM)not in index | – | – | – | 90.3%#1 | HELM Capabilities | |
| CaseLaw v2not in index | – | 53.1%#41 | – | – | Vals AI | |
| MedCodenot in index | – | 52.2%#14 | – | – | Vals AI | |
| MedScribenot in index | – | 72.0%#84 | – | – | Vals AI | |
| AA-Omniscience: accuracynot in index | 48.3%#69 | 55.8%#35 | – | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 10.0%#402 | 8.6%#434 | – | – | Artificial Analysis |
Instruction following
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| IFBench | 49.7%#175 | 70.4%#67 | – | – | Artificial Analysis | |
| MultiChallenge | – | – | – | 65.7%#5 | Scale AI SEAL | |
| IFEval (HELM) | – | – | – | 87.6%#13 | HELM Capabilities | |
| WildBench (HELM) | – | – | – | 85.9%#5 | HELM Capabilities | |
| LMArena Instruction Followingnot in index | – | – | – | 1473#32 | LMArena |
Human preference
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| LMArena Text | – | – | – | 1486#19 | LMArena | |
| LMArena Creative Writingnot in index | – | – | – | 1484#8 | LMArena | |
| LMArena Multi-turnnot in index | – | – | – | 1496#13 | LMArena | |
| LMArena Longer Queriesnot in index | – | – | – | 1491#27 | LMArena |
Multimodal
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| LMArena Vision | – | – | – | 1305#15 | LMArena | |
| MMMU-Pro | – | 80.2%#48 | – | – | Artificial Analysis | |
| VISTA | – | – | – | 51.5%#7 | Scale AI SEAL | |
| MMMU-Pro (official)not in index | – | – | – | 81.0%#1 | MMMU | |
| MMMU-Pro (Vals)not in index | – | 87.5%#14 | – | – | Vals AI | |
| MortgageTaxnot in index | – | 69.1%#7 | – | – | Vals AI | |
| SAGEnot in index | – | 47.6%#31 | – | – | Vals AI | |
| AudioMCnot in index | – | – | 54.6%#3 | – | Scale AI SEAL | |
| AudioMC (text output)not in index | – | – | 54.6%#2 | – | Scale AI SEAL | |
| VTBnot in index | – | – | – | 26.9%#5 | Scale AI SEAL | |
| GeoBenchnot in index | – | – | – | 84.0%#3 | GeoBench | |
| VPCTnot in index | – | – | – | 91.0%#1 | Epoch AI Benchmarking Hub |
Long context
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| AA-LCR | 74.0%#153 | 76.0%#134 | – | – | Artificial Analysis | |
| LMArena Documentnot in index | – | – | – | 1451#31 | LMArena |
Composite
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | – | – | 152.9#38 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index | 22.3#187 | 28.0#124 | – | – | Artificial Analysis | |
| HELM Capabilities meannot in index | – | – | – | 79.9%#5 | HELM Capabilities |
Safety & honesty
| Benchmark | low | high | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| FORTRESSnot in index | – | – | – | 41.7%#18 | Scale AI SEAL | |
| MASKnot in index | – | – | – | 42.6%#62 | Scale AI SEAL | |
| PropensityBenchnot in index | – | – | – | 52.9%#7 | Scale AI SEAL |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
See also
Data as of 5 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Gemini 3 Pro: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/gemini-3-pro, data as of 5 Oct 2026.