Gemini 3 Pro vs GPT-5.6 Sol
Full profiles: Gemini 3 Pro (Google) and GPT-5.6 Sol (OpenAI): every benchmark, price and rank.
Updated · Data from 16 sources
As of 29 Oct 2026, GPT-5.6 Sol is ahead of Gemini 3 Pro on quality (65.4 vs 60.2 on the BenchLeader Index). GPT-5.6 Sol leads in every category we measure both in.
Key facts (as of 29 Oct 2026)
- Gemini 3 Pro scores 60.2 on the BenchLeader Index and GPT-5.6 Sol scores 65.4 (BenchLeader, 29 Oct 2026).
- GPT-5.6 Sol costs $8.00 per 1M tokens blended (list price, 29 Oct 2026).
- Of the 14 benchmarks both models have, GPT-5.6 Sol leads 11 (BenchLeader, 29 Oct 2026).
Gemini 3 Pro benchmarks 
GPT-5.6 Sol benchmarks Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | GPT-5.6 Sol | 66 vs 58 category score; WeirdML 87.0% vs 69.9% | High |
| Agents & tool use | GPT-5.6 Sol | 67 vs 62 category score; Terminal-Bench 37.3% vs 69.4% | Medium |
| Maths | GPT-5.6 Sol | 71 vs 54 category score; OTIS Mock AIME 100.0% vs 91.4% | High |
| Reasoning | Either | 66 vs 65 category score; GPQA Diamond 92.6% vs 93.5% | Either |
| Knowledge | GPT-5.6 Sol | 64 vs 56 category score; PRBench Finance 50.5% vs 39.2% | High |
| Images and other media | Either | 66 vs 66 category score | Either |
| Following instructions | GPT-5.6 Sol | 71 vs 60 category score | High |
| Chat quality (human preference) | – | Only Gemini 3 Pro has an Arena rating (68 category score) | Not comparable |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- GPT-5.6 Sol (max) leads on quality: 65.4 vs 60.2.
- Gemini 3 Pro is stronger in human preference, reasoning.
- GPT-5.6 Sol (max) is stronger in agents & tools, coding, instruction following, knowledge, maths, multimodal, long context.
At a glance
| Spec | Gemini 3 Pro | GPT-5.6 Sol |
|---|---|---|
| Developer | OpenAI | |
| Released | 18 Nov 2025 | 9 Jul 2026 |
| Context window (tokens) | – | 1,050,000 |
| Compared at | Gemini 3 Pro | GPT-5.6 Sol (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | – | $4.00 / $20.00 / $0.400 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Gemini 3 Pro | GPT-5.6 Sol (max) | Leader |
|---|---|---|---|
| Reasoning | 65.6 | 65.1 | level |
| Coding | 57.8 | 65.8 | GPT-5.6 Sol |
| Agents & tools | 61.6 | 66.6 | GPT-5.6 Sol |
| Maths | 54.2 | 70.8 | GPT-5.6 Sol |
| Knowledge | 55.9 | 63.9 | GPT-5.6 Sol |
| Instruction following | 59.9 | 71.1 | GPT-5.6 Sol |
| Human preference | 67.8 | – | not comparable |
| Multimodal | 65.6 | 66.2 | level |
| Long context | – | 66.9 | not comparable |
Where sources disagree
Across the 14 benchmarks both have, Gemini 3 Pro leads 3, GPT-5.6 Sol leads 11. Independent sources split: Gemini 3 Pro leads on Arena Text; GPT-5.6 Sol leads on BenchLeader Index.
| Overall index | Gemini 3 Pro | GPT-5.6 Sol (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 60.2 | 65.4 | GPT-5.6 Sol |
| Arena Text | 1486 | 1485† | Gemini 3 Pro |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | Gemini 3 Pro | GPT-5.6 Sol (max) |
|---|---|---|
| Blended price per 1M tokens | – | $8.00 |
| Input / output per 1M | – / – | $4.00 / $20.00 |
| Cached input per 1M | – | $0.400 |
| Price per task: chat reply | – | $0.0076 |
| Price per task: summarize a 30-page report | – | $0.060 |
| Price per task: code edit | – | $0.054 |
| Price per task: agentic coding session | – | $0.320 |
| Price per task: structured extraction | – | $0.012 |
| Output speed | – | 85 tok/s |
| Time to first answer | – | 86.2 s |
| Time to a complete answer | – | 92.1 s |
Each model is compared at its best-ranked reasoning-effort setting. Gemini 3 Pro scores 60.2; Gemini 3 Pro (high) scores 60.1. GPT-5.6 Sol (max) scores 65.4 and takes 86 s to its first answer token; GPT-5.6 Sol (xhigh) scores 64.4 in 22 s, GPT-5.6 Sol (high) scores 63.6 in 11 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
175 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Gemini 3 Pro | GPT-5.6 Sol (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 60.2 | 65.4 |
| Agents & tools score | BenchLeader | 61.6 | 66.6 |
| Coding score | BenchLeader | 57.8 | 65.8 |
| Human preference score | BenchLeader | 67.8 | – |
| Instruction following score | BenchLeader | 59.9 | 71.1 |
| Knowledge score | BenchLeader | 55.9 | 63.9 |
| Maths score | BenchLeader | 54.2 | 70.8 |
| Multimodal score | BenchLeader | 65.6 | 66.2 |
| Reasoning score | BenchLeader | 65.6 | 65.1 |
| Long context score | BenchLeader | – | 66.9 |
| Blended price $/M | BenchLeader | – | $8.00 |
| Output speed | BenchLeader | – | 85 tok/s |
| Time to first answer | BenchLeader | – | 86.2 s |
| Context window | BenchLeader | – | 1,050,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 92.6% | 93.5% |
| Humanity's Last Exam | Scale AI / CAIS | 37.5% | – |
| SimpleBench | SimpleBench | 76.4% | 64.8%† |
| Arena Hard Prompts | Arena (LMArena) | 1502 | 1512† |
| LiveBench 1.0 Reasoning | LiveBench | – | 91.7% |
| GPQA Diamond (AA) | Artificial Analysis | 90.8%† | 94.1% |
| Humanity's Last Exam (AA) | Artificial Analysis | 39.7%† | 49.5% |
| GPQA Diamond (Vals) | Vals AI | 91.7%† | 95.2% |
| EnigmaEval | Scale AI SEAL | – | 37.1%† |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 80.1% | 67.0%† |
| GPQA Diamond (HELM) | HELM Capabilities | 80.3% | – |
| ARC-AGI-1 | ARC Prize | 75.0% | 96.5% |
| ARC-AGI-2 | ARC Prize | 54.0% | 92.5% |
| ARC-AGI-3 | ARC Prize | – | 7.8% |
| CritPt | Artificial Analysis | 9.1%† | 32.3% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 56.0% |
| MysteryMechanism | Vals AI | – | 33.3% |
| SciPredict | Scale AI SEAL | 25.3% | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 59.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 58.0% |
| CL-bench | Epoch AI Benchmarking Hub | 15.8% | – |
| LMCA | Epoch AI Benchmarking Hub | – | 58.4% |
| DTBench | Epoch AI Benchmarking Hub | – | 95.5% |
| ForecastBench | ForecastBench | 65.2% | 65.5% |
| BTF-3 | Epoch AI Benchmarking Hub | – | 13.7% |
Show all 175 benchmarks
| Metric | Publisher | Gemini 3 Pro | GPT-5.6 Sol (max) |
|---|---|---|---|
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 72.9% | – |
| SciCode | SciCode | – | 57.1% |
| WeirdML | WeirdML | 69.9% | 87.0% |
| FrontierCode | Cognition | – | 47.5%† |
| GSO-Bench | GSO-Bench | 18.6% | 76.5%† |
| Arena Coding | Arena (LMArena) | 1517 | 1534† |
| Arena WebDev | Arena (LMArena) | 1440 | 1616† |
| LiveBench 1.0 Coding | LiveBench | – | 83.9% |
| LiveCodeBench | Vals AI | 86.4% | 82.6% |
| IOI | Vals AI | – | 91.2% |
| SWE-bench (Vals) | Vals AI | 76.4%† | 96.2% |
| SWE-Bench Pro | Scale AI SEAL | 43.3% | – |
| SWE-bench Verified (bash only) | SWE-bench | 74.2% | – |
| SWE-bench Verified (any scaffold) | SWE-bench | 77.4% | – |
| Code Migration | Vals AI | – | 52.9% |
| ProgramBench | Vals AI | – | 1.5% |
| Vibe Code Bench 1-100 | Vals AI | – | 20.0% |
| Vibe Code Bench v1.1 | Vals AI | 14.3%† | 80.5% |
| SWE-Bench Pro (private) | Scale AI SEAL | 43.3% | – |
| SWE Atlas: Codebase QnA | Scale AI SEAL | – | 46.0%† |
| SWE Atlas: Test Writing | Scale AI SEAL | – | 45.9%† |
| MirrorCode | Epoch AI Benchmarking Hub | – | 20.0%† |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | – | 93.1%† |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 72.7% |
| CursorBench | Cursor | – | 41.7% |
| ALE-Bench | Epoch AI Benchmarking Hub | 1176.8 | 2176.9 |
| AlgoTune | AlgoTune | 1.8 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 32.2% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 39.9% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 88.0% |
| Startrise Frontend | Startrise | – | 66.2%† |
| LiveCodeBench (AA) | Artificial Analysis | 91.8%† | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 69.4% | 37.3% |
| OSWorld-Verified 2.0 | OSWorld | – | 27.3% |
| GDPval | OpenAI | 40.3% | – |
| Remote Labor Index | Scale AI / CAIS | 1.3% | – |
| Arena Agent | Arena (LMArena) | – | 6.1† |
| LiveBench Agentic Coding | LiveBench | – | 56.2% |
| Terminal-Bench Hard | Artificial Analysis | 41.7%† | 65.9% |
| τ²-Bench Telecom (AA) | Artificial Analysis | 87.1%† | 85.1% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 85.8% |
| MCP Atlas | Scale AI SEAL | 70.3% | – |
| HiL-Bench | Scale AI SEAL | – | 32.3%† |
| BFCL Overall | Berkeley Function Calling Leaderboard | 72.5% | – |
| τ²-bench | τ²-bench | 82.5%† | – |
| τ³-bench Banking | τ²-bench | 18.0%† | 46.9%† |
| τ³-Banking (AA) | Artificial Analysis | – | 44.3% |
| ITBench SRE (AA) | Artificial Analysis | – | 56.2% |
| Analyst Agent (AA) | Artificial Analysis | – | 47.5% |
| CUA-bench | Vals AI | – | 8.3% |
| CyberBench | Vals AI | – | 76.3% |
| Finance Agent v2 | Vals AI | – | 53.8% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 2.5% |
| Legal Research Bench | Vals AI | – | 48.1% |
| Poker Agent | Vals AI | 1078.9% | – |
| SkillsBench | Vals AI | – | 54.1% |
| SREBench | Vals AI | – | 30.5% |
| Tax Agent Bench | Vals AI | – | 31.1% |
| Terminal-Bench 2.0 (Vals) | Vals AI | 55.1%† | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 37.9% |
| Terminal-Bench Science | Vals AI | – | 20.0% |
| Time Horizon Index: KSP | Vals AI | – | 23.8% |
| Web Search Index | Vals AI | – | 43.6% |
| Arena Search | Arena (LMArena) | – | 1258† |
| BALROG | BALROG | 58.1% | 60.0% |
| DeepResearch Bench | DeepResearch Bench | 46.3%† | – |
| PostTrainBench | Epoch AI Benchmarking Hub | – | 36.2% |
| METR Time Horizons | METR | 71.0% | – |
| GBAEval | Epoch AI Benchmarking Hub | – | 52.6%† |
| Vending-Bench 2 | Andon Labs | 5478.2 | 9619.4† |
| AutomationBench | Artificial Analysis | – | 60.1% |
| GDP.pdf (AA) | Artificial Analysis | – | 27.2% |
| EnterpriseOps-Gym | Artificial Analysis | – | 42.9% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1478 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 22.4% |
| FACTS Search | – | 88.5%† | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 89.1% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 82.9% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 91.4% | 100.0% |
| ProofBench | Vals AI | 20.0% | 83.0% |
| LiveBench Mathematics | LiveBench | – | 96.2% |
| AIME (Vals) | Vals AI | 96.7%† | – |
| MGSM | Vals AI | 93.9%† | – |
| AIME 2026 | MathArena | 91.7% | – |
| HMMT February 2026 | MathArena | 86.4% | – |
| MathArena Apex | MathArena | 23.4% | – |
| Omni-MATH (HELM) | HELM Capabilities | 55.6% | – |
| MATH 500 | Vals AI | 96.4%† | – |
| Arena Maths | Arena (LMArena) | 1477 | 1496† |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 69.7% |
| LiveBench 1.0 Data Analysis | LiveBench | – | 79.8% |
| MMLU-Pro | Vals AI | 90.1% | 89.1% |
| LegalBench | Vals AI | 87.0%† | 87.0% |
| CorpFin | Vals AI | 63.7%† | 64.4% |
| TaxEval | Vals AI | 72.6%† | 74.8% |
| MedQA | Vals AI | 96.0%† | – |
| PRBench Finance | Scale AI SEAL | 39.2% | 50.5% |
| PRBench Legal | Scale AI SEAL | 40.6% | 50.5% |
| MultiNRC | Scale AI SEAL | 59.0% | – |
| MMLU-Pro (HELM) | HELM Capabilities | 90.3% | – |
| BioMysteryBench | Vals AI | – | 71.1% |
| CaseLaw v2 | Vals AI | 53.1%† | – |
| Excel Modeling Benchmark | Vals AI | – | 72.3% |
| MedCode | Vals AI | 52.2%† | 44.0% |
| MedScribe | Vals AI | 72.0%† | 85.2% |
| Public Benefits Bench v1.1 | Vals AI | – | 66.5% |
| DrugDiscoveryBench | Scale AI SEAL | – | 56.5% |
| EBR-bench | Epoch AI Benchmarking Hub | – | 44.8% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 30.7% |
| Global-MMLU-Lite (AA) | Artificial Analysis | 92.2%† | – |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 87.7% |
| LiveBench Instruction Following | LiveBench | – | 71.8% |
| IFBench | Artificial Analysis | 70.4%† | 72.7% |
| MultiChallenge | Scale AI SEAL | 65.7% | – |
| TutorBench | Scale AI SEAL | 53.7% | – |
| IFEval (HELM) | HELM Capabilities | 87.6% | – |
| WildBench (HELM) | HELM Capabilities | 85.9% | – |
| Arena Instruction Following | Arena (LMArena) | 1473 | 1491† |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1486 | 1485† |
| EQ-Bench 4 | EQ-Bench | – | 1236† |
| Arena Creative Writing | Arena (LMArena) | 1485 | 1470† |
| Arena Multi-turn | Arena (LMArena) | 1496 | 1490† |
| Arena Longer Queries | Arena (LMArena) | 1491 | 1499† |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1305 | 1281† |
| MMMU-Pro | Artificial Analysis | 80.2%† | 83.4% |
| VISTA | Scale AI SEAL | 51.5% | – |
| MMMU-Pro (official) | MMMU | 81.0% | – |
| MMMU-Pro (Vals) | Vals AI | 87.5%† | 88.8% |
| MortgageTax | Vals AI | 69.1%† | 67.3% |
| AudioMC | Scale AI SEAL | 54.6%† | – |
| AudioMC (text output) | Scale AI SEAL | 54.6%† | – |
| VTB | Scale AI SEAL | 26.9% | – |
| GeoBench | GeoBench | 84.0% | – |
| VPCT | Epoch AI Benchmarking Hub | 91.0% | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 33.6%† |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 76.0%† | 84.0% |
| Arena Document | Arena (LMArena) | 1451 | 1489† |
| MLCR | Artificial Analysis | – | 30.0% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 153.1 | 162.8† |
| LiveBench 1.0 | LiveBench | – | 81.0% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 28.0† | 47.0 |
| AA Progress Index v1 | Artificial Analysis | 290.7† | 331.5 |
| HELM Capabilities mean | HELM Capabilities | 79.9% | – |
| Vals RSI Index | Vals AI | – | 23.9% |
| Vals Science Index | Vals AI | – | 41.5% |
| Vals Multimodal Index | Vals AI | – | 72.6% |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 41.7% | 20.1%† |
| MASK | Scale AI SEAL | 42.6% | – |
| PropensityBench | Scale AI SEAL | 52.9% | – |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 5.6† | – |
Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.
What changed
- GPT-5.6 Sol (max): 2 new results (AA Progress Index v1, CritPt v2 hard subset (AA)).
- GPT-5.6 Sol (max): 1 new result (AA-Briefcase v1.1).
- Gemini 3 Pro: 1 score revision.
- GPT-5.6 Sol (max): 3 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index, Vals Science Index).
- GPT-5.6 Sol (max): 1 score revision.
- Gemini 3 Pro: 1 score revision.
- GPT-5.6 Sol (max): 1 new result (ForecastBench).
- GPT-5.6 Sol (max): 5 new results (AutomationBench, GDP.pdf (AA), MLCR…).
- GPT-5.6 Sol (max): 1 score revision.
- Gemini 3 Pro: BenchLeader Index 60.9 → 60.4.
Related comparisons
- Gemini 3 Pro vs Claude Opus 5.5
- Gemini 3 Pro vs GPT-6 Astra
- Gemini 3 Pro vs GPT-6.1 Sol
- GPT-5.6 Sol vs Claude Opus 5.5
- GPT-5.6 Sol vs GPT-6 Astra
- GPT-5.6 Sol vs GPT-6.1 Sol
- GPT-5.6 Sol vs Claude Fable 5.1
- Gemini 3 Pro vs GPT-5.5
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Gemini 3 Pro vs GPT-5.6 Sol: questions
- Is GPT-5.6 Sol better than Gemini 3 Pro?
- GPT-5.6 Sol (max) leads on quality: 65.4 vs 60.2. The BenchLeader Index combines every independent quality benchmark; GPT-5.6 Sol (max) is ahead overall as of 29 Oct 2026, but check the category scores for your use.
- Is Gemini 3 Pro or GPT-5.6 Sol better for coding?
- GPT-5.6 Sol scores higher in coding (66 vs 58 on the category index, where 50 is average). On LiveCodeBench, the top shared coding benchmark, it is 86.4% for Gemini 3 Pro against 82.6% for GPT-5.6 Sol.
- Is Gemini 3 Pro or GPT-5.6 Sol better for agents and tool use?
- GPT-5.6 Sol scores higher in agentic tasks (67 vs 62 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 69.4% for Gemini 3 Pro against 37.3% for GPT-5.6 Sol.
- Do independent benchmarks agree on Gemini 3 Pro vs GPT-5.6 Sol?
- Across the 14 benchmarks both have, Gemini 3 Pro leads 3, GPT-5.6 Sol leads 11. Independent sources split: Gemini 3 Pro leads on Arena Text; GPT-5.6 Sol leads on BenchLeader Index.
- When was GPT-5.6 Sol released?
- GPT-5.6 Sol was released on 9 Jul 2026.