Claude Sonnet 5.5 vs Gemini 3 Pro
Full profiles: Claude Sonnet 5.5 (Anthropic) and Gemini 3 Pro (Google): every benchmark, price and rank.
Updated · Data from 19 sources
As of 10 Nov 2026, Claude Sonnet 5.5 is ahead of Gemini 3 Pro on quality (64.9 vs 60.2 on the BenchLeader Index). Claude Sonnet 5.5 leads in every category we measure both in.
Key facts (as of 10 Nov 2026)
- Claude Sonnet 5.5 scores 64.9 on the BenchLeader Index and Gemini 3 Pro scores 60.2 (BenchLeader, 10 Nov 2026).
- Claude Sonnet 5.5 costs $4.00 per 1M tokens blended (list price, 10 Nov 2026).
- Of the 5 benchmarks both models have, Claude Sonnet 5.5 leads 4 (BenchLeader, 10 Nov 2026).
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 | Claude Sonnet 5.5 | 72 vs 58 category score | High |
| Agents & tool use | Claude Sonnet 5.5 | 71 vs 61 category score; Terminal-Bench 63.9% vs 69.4% | High |
| Maths | Claude Sonnet 5.5 | 72 vs 54 category score; OTIS Mock AIME 100.0% vs 91.4% | High |
| Reasoning | Claude Sonnet 5.5 | 68 vs 66 category score; GPQA Diamond 95.6% vs 92.6% | Medium |
| Knowledge | Claude Sonnet 5.5 | 58 vs 56 category score | Medium |
| 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
- Claude Sonnet 5.5 (max) leads on quality: 64.9 vs 60.2.
- Claude Sonnet 5.5 (max) is stronger in agents & tools, coding, knowledge, long context, maths, reasoning.
- Gemini 3 Pro is stronger in human preference, instruction following, multimodal.
At a glance
| Spec | Claude Sonnet 5.5 | Gemini 3 Pro |
|---|---|---|
| Developer | Anthropic | |
| Released | 28 Sep 2026 | 18 Nov 2025 |
| Context window (tokens) | 1,000,000 | – |
| Compared at | Claude Sonnet 5.5 (max) | Gemini 3 Pro |
| Open weights | No | No |
| Price in / out / cached input per 1M | $2.00 / $10.00 / $0.100 | – |
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 | Claude Sonnet 5.5 (max) | Gemini 3 Pro | Leader |
|---|---|---|---|
| Reasoning | 68.0 | 65.5 | Claude Sonnet 5.5 |
| Coding | 71.6 | 57.8 | Claude Sonnet 5.5 |
| Agents & tools | 70.9 | 61.3 | Claude Sonnet 5.5 |
| Maths | 71.6 | 54.2 | Claude Sonnet 5.5 |
| Knowledge | 57.8 | 56.2 | Claude Sonnet 5.5 |
| Instruction following | – | 60.1 | not comparable |
| Human preference | – | 67.7 | not comparable |
| Multimodal | – | 65.6 | not comparable |
| Long context | 66.1 | – | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 5 benchmarks both have, Claude Sonnet 5.5 leads 4, Gemini 3 Pro leads 1. Independent sources split: Claude Sonnet 5.5 leads on BenchLeader Index; Gemini 3 Pro leads on Arena Text.
| Overall index | Claude Sonnet 5.5 (max) | Gemini 3 Pro | Leader |
|---|---|---|---|
| BenchLeader Index | 64.9 | 60.2 | Claude Sonnet 5.5 |
| Arena Text | 1473† | 1486 | 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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Claude Sonnet 5.5 (max) | Gemini 3 Pro |
|---|---|---|
| Blended price per 1M tokens | $4.00 | – |
| Input / output per 1M | $2.00 / $10.00 | – / – |
| Cached input per 1M | $0.100 | – |
| Price per task: chat reply | $0.0038 | – |
| Price per task: summarize a 30-page report | $0.030 | – |
| Price per task: code edit | $0.027 | – |
| Price per task: agentic coding session | $0.160 | – |
| Price per task: structured extraction | $0.0060 | – |
| Agentic coding session, input mostly cached | $0.074 | – |
| Cost per benchmark task (AA Index) | $10.02 | – |
| Output tokens per task (AA Index) | 285k | – |
| Of which reasoning | 206k | – |
| Time per task (AA Index) | 31 min | – |
| Output speed | 151 tok/s | – |
| Time to first answer | 260.6 s | – |
| Time to a complete answer | 517.1 s | – |
Each model is compared at its best-ranked reasoning-effort setting. Claude Sonnet 5.5 (max) scores 64.9 and takes 261 s to its first answer token; Claude Sonnet 5.5 (xhigh) scores 62.7 in 26 s, Claude Sonnet 5.5 (high) scores 58.1 in 10 s. Gemini 3 Pro scores 60.2; Gemini 3 Pro (high) scores 60.1. 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
187 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 | Claude Sonnet 5.5 (max) | Gemini 3 Pro |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.9 | 60.2 |
| Agents & tools score | BenchLeader | 70.9 | 61.3 |
| Coding score | BenchLeader | 71.6 | 57.8 |
| Knowledge score | BenchLeader | 57.8 | 56.2 |
| Long context score | BenchLeader | 66.1 | – |
| Maths score | BenchLeader | 71.6 | 54.2 |
| Reasoning score | BenchLeader | 68.0 | 65.5 |
| Human preference score | BenchLeader | – | 67.7 |
| Instruction following score | BenchLeader | – | 60.1 |
| Multimodal score | BenchLeader | – | 65.6 |
| Blended price $/M | BenchLeader | $4.00 | – |
| Output speed | BenchLeader | 151 tok/s | – |
| Time to first answer | BenchLeader | 260.6 s | – |
| Context window | BenchLeader | 1,000,000 tokens | – |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 95.6% | 92.6% |
| Humanity's Last Exam | Scale AI / CAIS | 46.1%† | 37.5% |
| SimpleBench | SimpleBench | – | 76.4% |
| Arena Hard Prompts | Arena (LMArena) | 1498† | 1502 |
| LiveBench 2.0 Reasoning | LiveBench | 91.6%† | – |
| LiveBench 1.0 Reasoning | LiveBench | 91.6% | – |
| GPQA Diamond (AA) | Artificial Analysis | – | 90.8%† |
| Humanity's Last Exam (AA) | Artificial Analysis | 55.0% | 39.7%† |
| HLE-Diamond (AA) | Artificial Analysis | 53.3% | – |
| GPQA Diamond (Vals) | Vals AI | – | 91.7%† |
| Kagi LLM Benchmark | Kagi LLM Benchmark | – | 80.1% |
| GPQA Diamond (HELM) | HELM Capabilities | – | 80.3% |
| ARC-AGI-1 | ARC Prize | 96.5% | 75.0% |
| ARC-AGI-2 | ARC Prize | 83.9%† | 54.0% |
| ARC-AGI-3 | ARC Prize | 72.4%† | – |
| CritPt | Artificial Analysis | 31.4% | 9.1%† |
| CritPt v2 hard subset (AA) | Artificial Analysis | 59.0% | – |
| MysteryMechanism | Vals AI | 49.1%† | – |
| SciPredict | Scale AI SEAL | – | 25.3% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 59.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 65.0% | – |
| CL-bench | Epoch AI Benchmarking Hub | – | 15.8% |
| LMCA | Epoch AI Benchmarking Hub | 68.3% | – |
| DTBench | Epoch AI Benchmarking Hub | 97.3% | – |
| ForecastBench | ForecastBench | – | 65.0% |
Show all 187 benchmarks
| Metric | Publisher | Claude Sonnet 5.5 (max) | Gemini 3 Pro |
|---|---|---|---|
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 72.9% |
| SciCode | SciCode | 61.0% | – |
| WeirdML | WeirdML | – | 69.9% |
| FrontierCode | Cognition | 52.1%† | – |
| GSO-Bench | GSO-Bench | – | 18.6% |
| Arena Coding | Arena (LMArena) | 1516† | 1517 |
| Arena WebDev | Arena (LMArena) | 1774† | 1441 |
| LiveBench 2.0 Coding | LiveBench | 77.2%† | – |
| LiveBench 1.0 Coding | LiveBench | 91.4% | – |
| LiveCodeBench | Vals AI | – | 86.4% |
| IOI | Vals AI | 83.1%† | – |
| SWE-bench (Vals) | Vals AI | – | 76.4%† |
| 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 | 69.8%† | – |
| Code Migration v1.1 | Vals AI | 86.9%† | – |
| ProgramBench | Vals AI | 6.5%† | – |
| SWE-bench Multimodal | Vals AI | 58.3%† | – |
| Vibe Code Bench v1.1 | Vals AI | 92.4%† | 14.3%† |
| SWE-Bench Pro (private) | Scale AI SEAL | – | 43.3% |
| CursorBench | Cursor | 55.5% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1819.1† | 1176.8 |
| AlgoTune | AlgoTune | – | 1.8 |
| FrontierSWE | Epoch AI Benchmarking Hub | 61.9% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 63.6% | – |
| Startrise Frontend | Startrise | 75.9%† | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 60.4† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 91.3† | – |
| Design Arena Website | Design Arena | 1314† | 1249 |
| FrontierCode 1.1 (AA) | Artificial Analysis | 45.8% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 41.7% | – |
| LiveCodeBench (AA) | Artificial Analysis | – | 91.8%† |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 63.9% | 69.4% |
| GDPval | OpenAI | – | 40.3% |
| Remote Labor Index | Scale AI / CAIS | – | 1.3% |
| APEX-Agents | Mercor | 75.5% | – |
| Arena Agent | Arena (LMArena) | 16 | – |
| LiveBench Long Agentic | LiveBench | 63.4%† | – |
| LiveBench Browser | LiveBench | 89.3%† | – |
| LiveBench Agentic Coding | LiveBench | 56.3% | – |
| Terminal-Bench Hard | Artificial Analysis | – | 41.7%† |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 87.1%† |
| Terminal-Bench 2.1 (Vals) | Vals AI | 83.2%† | – |
| MCP Atlas | Scale AI SEAL | – | 70.3% |
| BFCL Overall | Berkeley Function Calling Leaderboard | – | 72.5% |
| τ²-bench | τ²-bench | – | 82.5%† |
| τ³-bench Banking | τ²-bench | – | 18.0%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 66.9% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1838 | – |
| Analyst Agent (AA) | Artificial Analysis | 57.5% | – |
| CyberBench | Vals AI | 59.6%† | – |
| Finance Agent v2 | Vals AI | 58.1%† | – |
| Finance Agent v2.1 | Vals AI | 67.3%† | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 10.4%† | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 2.9%† | – |
| Legal Research Bench | Vals AI | 48.1%† | – |
| Poker Agent | Vals AI | – | 1078.9% |
| SREBench | Vals AI | 30.1%† | – |
| Tax Agent Bench | Vals AI | 42.0%† | – |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 55.1%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 64.1%† | – |
| Terminal-Bench Science | Vals AI | 47.1%† | – |
| Arena Search | Arena (LMArena) | – | 1201 |
| BALROG | BALROG | – | 58.1% |
| DeepResearch Bench | DeepResearch Bench | – | 46.3%† |
| METR Time Horizons | METR | – | 71.0% |
| Vending-Bench 2 | Andon Labs | 11165.3† | 5478.2 |
| AutomationBench | Artificial Analysis | 71.8% | – |
| GDP.pdf (AA) | Artificial Analysis | 25.8% | – |
| Harvey LAB-AA v1.1 | Harvey | 2.8% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1816 | – |
| GDPx | GDPx by SemiAnalysis | 8.2% | – |
| Design Arena Agentic | Design Arena | 1281† | 1073 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 53.3% | – |
| FACTS Search | 86.8%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 88.8% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 80.5% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | 91.4% |
| ProofBench | Vals AI | 100.0% | 20.0% |
| LiveBench Mathematics | LiveBench | 96.1% | – |
| 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) | 1490† | 1476 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 46.5% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 59.5%† | – |
| LiveBench Research | LiveBench | 88.0%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 59.5% | – |
| AA-Omniscience v1.1 | Artificial Analysis | 30.5 | – |
| MMLU-Pro | Vals AI | – | 90.1% |
| LegalBench | Vals AI | – | 87.0%† |
| CorpFin | Vals AI | – | 63.7%† |
| TaxEval | Vals AI | – | 72.6%† |
| MedQA | Vals AI | – | 96.0%† |
| PRBench Finance | Scale AI SEAL | – | 39.2% |
| PRBench Legal | Scale AI SEAL | – | 40.6% |
| MultiNRC | Scale AI SEAL | – | 59.0% |
| MMLU-Pro (HELM) | HELM Capabilities | – | 90.3% |
| BioMysteryBench | Vals AI | 81.1%† | – |
| CaseLaw v2 | Vals AI | – | 53.1%† |
| ClaimBench | Vals AI | 100.0%† | – |
| Excel Modeling Benchmark | Vals AI | 75.7%† | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 75.9%† | – |
| MedCode | Vals AI | 52.9%† | 52.2%† |
| MedScribe | Vals AI | 91.1%† | 72.0%† |
| Public Benefits Bench v1.1 | Vals AI | 67.2%† | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 31.4% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 51.5% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 56.7% | – |
| Global-MMLU-Lite (AA) | Artificial Analysis | – | 92.2%† |
| HealthBench Professional (AA) | OpenAI | 63.0% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 78.0% | – |
| LiveBench Instruction Following | LiveBench | 56.8% | – |
| IFBench | Artificial Analysis | – | 70.4%† |
| 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) | 1480† | 1473 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1473† | 1486 |
| Arena Creative Writing | Arena (LMArena) | 1465† | 1484 |
| Arena Multi-turn | Arena (LMArena) | 1469† | 1496 |
| Arena Longer Queries | Arena (LMArena) | 1489† | 1491 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1284† | 1305 |
| LiveBench Design | LiveBench | 81.3%† | – |
| MMMU-Pro | Artificial Analysis | – | 80.2%† |
| VISTA | Scale AI SEAL | – | 51.5% |
| MMMU-Pro (official) | MMMU | – | 81.0% |
| MMMU-Pro (Vals) | Vals AI | – | 87.5%† |
| MortgageTax | Vals AI | – | 69.1%† |
| SAGE | Vals AI | 88.0%† | – |
| 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 | 39.3%† | – |
| Code2Video-AA | Artificial Analysis | 1443 | – |
| AA-3D | Artificial Analysis | 1204 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.7% | 76.0%† |
| Arena Document | Arena (LMArena) | – | 1451 |
| MLCR | Artificial Analysis | 41.7% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 166.3† | 152.9 |
| LiveBench 2.0 | LiveBench | 77.0%† | – |
| LiveBench 1.0 | LiveBench | 75.7% | – |
| AA Intelligence Index v5.0 | Artificial Analysis | 54.5 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 56 | 28.0† |
| AA Progress Index v1 | Artificial Analysis | 350.5 | 290.7† |
| Vals Index | Vals AI | 70.8† | – |
| HELM Capabilities mean | HELM Capabilities | – | 79.9% |
| Vals Finance Index | Vals AI | 64.5%† | – |
| Vals Science Index | Vals AI | 59.1%† | – |
| Vals Router Index | Vals AI | 69.0%† | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 41.7% |
| MASK | Scale AI SEAL | – | 42.6% |
| PropensityBench | Scale AI SEAL | – | 52.9% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | – | 5.6† |
Data as of 2026-11-10. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Claude Sonnet 5.5 (max): 2 score revisions.
- Gemini 3 Pro: 1 new result (Arena Search).
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 new result (MirrorCode).
- Claude Sonnet 5.5 (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $5.46/M to $10.02/M (83% up).
- Claude Sonnet 5.5 (max): 1 score revision.
- Gemini 3 Pro: 1 score revision.
- Claude Sonnet 5.5 (max): 1 new result (ARC-AGI-1); 1 score revision.
Related comparisons
- Claude Sonnet 5.5 vs Claude Fable 5.2
- Claude Sonnet 5.5 vs Claude Opus 5.5
- Claude Sonnet 5.5 vs Gemini 4 Carbon
- Gemini 3 Pro vs Claude Fable 5.2
- Gemini 3 Pro vs Claude Opus 5.5
- Gemini 3 Pro vs Gemini 4 Carbon
- Gemini 3 Pro vs GPT-6 Astra
- Claude Sonnet 5.5 vs GPT-6.1 Sol
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Sonnet 5.5 vs Gemini 3 Pro: questions
- Is Claude Sonnet 5.5 better than Gemini 3 Pro?
- Claude Sonnet 5.5 (max) leads on quality: 64.9 vs 60.2. The BenchLeader Index combines every independent quality benchmark; Claude Sonnet 5.5 (max) is ahead overall as of 10 Nov 2026, but check the category scores for your use.
- Is Claude Sonnet 5.5 or Gemini 3 Pro better for coding?
- Claude Sonnet 5.5 scores higher in coding (72 vs 58 on the category index, where 50 is average).
- Is Claude Sonnet 5.5 or Gemini 3 Pro better for agents and tool use?
- Claude Sonnet 5.5 scores higher in agentic tasks (71 vs 61 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 63.9% for Claude Sonnet 5.5 against 69.4% for Gemini 3 Pro.
- Do independent benchmarks agree on Claude Sonnet 5.5 vs Gemini 3 Pro?
- Across the 5 benchmarks both have, Claude Sonnet 5.5 leads 4, Gemini 3 Pro leads 1. Independent sources split: Claude Sonnet 5.5 leads on BenchLeader Index; Gemini 3 Pro leads on Arena Text.
- When was Claude Sonnet 5.5 released?
- Claude Sonnet 5.5 was released on 28 Sep 2026.