Claude Sonnet 5.5 vs Gemini 4 Carbon
Full profiles: Claude Sonnet 5.5 (Anthropic) and Gemini 4 Carbon (Google): every benchmark, price and rank.
Updated · Data from 9 sources
As of 29 Oct 2026, Claude Sonnet 5.5 and Gemini 4 Carbon are neck and neck on quality (64.9 vs 65.1 on the BenchLeader Index, inside the ±6.8 margin), and Claude Sonnet 5.5 is 2.0× cheaper at $4.00 vs $8.00 per 1M tokens blended. Choose Claude Sonnet 5.5 for long context (66 vs 65), where it also streams faster; choose Gemini 4 Carbon for fast first answers (103.1 s vs 448.1 s) and knowledge (76 vs 58) and reasoning (79 vs 69).
Key facts (as of 29 Oct 2026)
- Claude Sonnet 5.5 scores 64.9 on the BenchLeader Index and Gemini 4 Carbon scores 65.1 (BenchLeader, 29 Oct 2026).
- Claude Sonnet 5.5 costs $4.00 per 1M tokens blended (list price, 29 Oct 2026).
- Gemini 4 Carbon costs $8.00 per 1M tokens blended (list price, 29 Oct 2026).
- Claude Sonnet 5.5 streams faster than Gemini 4 Carbon (Artificial Analysis, 7-day median, 29 Oct 2026).
- Of the 17 benchmarks both models have, Gemini 4 Carbon leads 14 (BenchLeader, 29 Oct 2026).
Claude Sonnet 5.5 benchmarks max Anthropic
Gemini 4 Carbon benchmarks high GoogleOpen in the comparison toolWhich 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 | Either | 71 vs 72 category score; FrontierCode 2.0 (AA) 41.7% vs 40.6% | Either |
| Reasoning | Gemini 4 Carbon | 79 vs 69 category score; HLE-Diamond (AA) 69.1% vs 53.3% | High |
| Knowledge | Gemini 4 Carbon | 76 vs 58 category score; AA-Omniscience v1.1 53.5 vs 30.5 | High |
| Long documents | Claude Sonnet 5.5 | 66 vs 65 category score; AA-LCR v1.1 82.7% vs 79.3% | Medium |
| Lowest cost | Claude Sonnet 5.5 | $4.00 vs $8.00 per 1M blended; agentic coding session $0.160 vs $0.320 | – |
| Fastest first answer | Gemini 4 Carbon | 103.1 s (Gemini 4 Carbon (high)) vs 448.1 s (Claude Sonnet 5.5 (max)) to the first answer token | – |
| 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) and Gemini 4 Carbon (high) are neck and neck on quality (64.9 vs 65.1, within the ±6.8 margin).
- Claude Sonnet 5.5 (max) is stronger in agents & tools, long context, maths.
- Gemini 4 Carbon (high) is stronger in coding, knowledge, reasoning.
- Claude Sonnet 5.5 (max) is 2.0× cheaper ($4.00 vs $8.00 per 1M blended).
- Claude Sonnet 5.5 (max) streams 1.4× faster (137 vs 100 tokens per second).
At a glance
| Spec | Claude Sonnet 5.5 | Gemini 4 Carbon |
|---|---|---|
| Developer | Anthropic | |
| Released | 28 Sept 2026 | 28 Oct 2026 |
| Context window (tokens) | 1,000,000 | 1,000,000 |
| Compared at | Claude Sonnet 5.5 (max) | Gemini 4 Carbon (high) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $2.00 / $10.00 / $0.100 | $4.00 / $20.00 / – |
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 4 Carbon (high) | Leader |
|---|---|---|---|
| Reasoning | 68.6 | 78.9 | Gemini 4 Carbon |
| Coding | 71.1 | 71.7 | level |
| Agents & tools | 70.1 | – | not comparable |
| Maths | 72.1 | – | not comparable |
| Knowledge | 58.1 | 75.8 | Gemini 4 Carbon |
| Long context | 66.2 | 64.5 | Claude Sonnet 5.5 |
Where sources disagree
Across the 17 benchmarks both have, Claude Sonnet 5.5 leads 3, Gemini 4 Carbon leads 14. Independent sources split: Claude Sonnet 5.5 leads on Vals Index; Gemini 4 Carbon leads on AA Intelligence Index v5.0.
| Overall index | Claude Sonnet 5.5 (max) | Gemini 4 Carbon (high) | Leader |
|---|---|---|---|
| BenchLeader Index | 64.9 | 65.1 | neck and neck |
| AA Intelligence Index v5.0 | 54.2 | 59.4 | Gemini 4 Carbon |
| Vals Index | 70.8† | 70.4 | Claude Sonnet 5.5 |
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 | Claude Sonnet 5.5 (max) | Gemini 4 Carbon (high) |
|---|---|---|
| Blended price per 1M tokens | $4.00 | $8.00 |
| Input / output per 1M | $2.00 / $10.00 | $4.00 / $20.00 |
| Cached input per 1M | $0.100 | – |
| Price per task: chat reply | $0.0038 | $0.0076 |
| Price per task: summarize a 30-page report | $0.030 | $0.060 |
| Price per task: code edit | $0.027 | $0.054 |
| Price per task: agentic coding session | $0.160 | $0.320 |
| Price per task: structured extraction | $0.0060 | $0.012 |
| Cost to run a full benchmark suite | $10.02 | $7.76 |
| Output speed | 137 tok/s | 100 tok/s |
| Time to first answer | 448.1 s | 103.1 s |
| Time to a complete answer | 451.8 s | 108.1 s |
Per token is not per task: on Artificial Analysis' full suite Claude Sonnet 5.5 (max) cost $10.02 and Gemini 4 Carbon (high) $7.76, because Claude Sonnet 5.5 (max) used about 2.6× as many tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. Claude Sonnet 5.5 (max) scores 64.9 and takes 448 s to its first answer token; Claude Sonnet 5.5 (xhigh) scores 63.1 in 28 s, Claude Sonnet 5.5 (high) scores 58.1 in 11 s. Gemini 4 Carbon (high) scores 65.1 and takes 103 s to its first answer token. 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
106 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 4 Carbon (high) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.9 | 65.1 |
| Agents & tools score | BenchLeader | 70.1 | – |
| Coding score | BenchLeader | 71.1 | 71.7 |
| Knowledge score | BenchLeader | 58.1 | 75.8 |
| Long context score | BenchLeader | 66.2 | 64.5 |
| Maths score | BenchLeader | 72.1 | – |
| Reasoning score | BenchLeader | 68.6 | 78.9 |
| Blended price $/M | BenchLeader | $4.00 | $8.00 |
| Output speed | BenchLeader | 137 tok/s | 100 tok/s |
| Time to first answer | BenchLeader | 448.1 s | 103.1 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 95.6% | – |
| Humanity's Last Exam | Scale AI / CAIS | 46.1%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1505† | – |
| LiveBench 2.0 Reasoning | LiveBench | 91.6%† | – |
| LiveBench 1.0 Reasoning | LiveBench | 91.6% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 55.0% | 60.4% |
| HLE-Diamond (AA) | Artificial Analysis | 53.3% | 69.1% |
| ARC-AGI-1 | ARC Prize | 96.5% | – |
| ARC-AGI-2 | ARC Prize | 83.9%† | – |
| ARC-AGI-3 | ARC Prize | 72.4%† | – |
| CritPt | Artificial Analysis | 31.4% | 36.0% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 56.0% | 63.0% |
| MysteryMechanism | Vals AI | 49.1%† | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 59.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 65.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 68.3% | – |
| DTBench | Epoch AI Benchmarking Hub | 97.3% | – |
| Coding | |||
| SciCode | SciCode | 61.0% | 64.2% |
| FrontierCode | Cognition | 52.1%† | – |
| Arena Coding | Arena (LMArena) | 1528† | – |
| Arena WebDev | Arena (LMArena) | 1769† | – |
| LiveBench 2.0 Coding | LiveBench | 94.7%† | – |
| LiveBench 1.0 Coding | LiveBench | 91.4% | – |
| IOI | Vals AI | 83.1%† | – |
| Code Migration | Vals AI | 69.8%† | – |
Show all 106 benchmarks
| Metric | Publisher | Claude Sonnet 5.5 (max) | Gemini 4 Carbon (high) |
|---|---|---|---|
| Coding | |||
| 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%† | 89.1% |
| CursorBench | Cursor | 55.5% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1819.1† | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 61.9% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 63.6% | 65.2% |
| Startrise Frontend | Startrise | 75.9%† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 45.8% | 48.5% |
| FrontierCode 2.0 (AA) | Artificial Analysis | 41.7% | 40.6% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 61.8% | – |
| APEX-Agents | Mercor | 75.5% | – |
| Arena Agent | Arena (LMArena) | 14 | – |
| LiveBench Long Agentic | LiveBench | 63.4%† | – |
| LiveBench Browser | LiveBench | 89.3%† | – |
| LiveBench Agentic Coding | LiveBench | 56.3% | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | 83.2%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 66.9% | – |
| 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%† | 67.2% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 10.4%† | 17.5% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 2.9%† | – |
| Legal Research Bench | Vals AI | 48.1%† | 55.8% |
| SREBench | Vals AI | 30.1%† | – |
| Tax Agent Bench | Vals AI | 42.0%† | 48.9% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 64.1%† | 63.1% |
| Terminal-Bench Science | Vals AI | 47.1%† | – |
| Vending-Bench 2 | Andon Labs | 11165.3† | 16484.2† |
| AutomationBench | Artificial Analysis | 71.8% | 77.8% |
| GDP.pdf (AA) | Artificial Analysis | 25.8% | 28.4% |
| Harvey LAB-AA v1.1 | Harvey | 2.8% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1812 | 1609 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 53.3% | 64.8% |
| 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% | – |
| ProofBench | Vals AI | 100.0% | – |
| LiveBench Mathematics | LiveBench | 96.1% | – |
| Arena Maths | Arena (LMArena) | 1501† | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 46.5% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 59.5%† | – |
| LiveBench Research | LiveBench | 83.6%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 59.5% | – |
| AA-Omniscience v1.1 | Artificial Analysis | 30.5 | 53.5 |
| BioMysteryBench | Vals AI | 81.1%† | – |
| ClaimBench | Vals AI | 100.0%† | – |
| Excel Modeling Benchmark | Vals AI | 75.7%† | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 75.9%† | 76.5% |
| MedCode | Vals AI | 52.9%† | – |
| MedScribe | Vals AI | 91.1%† | – |
| 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% | 58.3% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 56.7% | 88.6% |
| Instruction following | |||
| LiveBench Language | LiveBench | 78.0% | – |
| LiveBench Instruction Following | LiveBench | 56.8% | – |
| Arena Instruction Following | Arena (LMArena) | 1485† | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1478† | – |
| Arena Creative Writing | Arena (LMArena) | 1466† | – |
| Arena Multi-turn | Arena (LMArena) | 1474† | – |
| Arena Longer Queries | Arena (LMArena) | 1500† | – |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1287† | – |
| LiveBench Design | LiveBench | 85.0%† | – |
| SAGE | Vals AI | 88.0%† | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 39.3%† | 58.6%† |
| AA-3D | Artificial Analysis | 1199 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.7% | 79.3% |
| MLCR | Artificial Analysis | 41.7% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 166.2† | – |
| LiveBench 2.0 | LiveBench | 80.0%† | – |
| LiveBench 1.0 | LiveBench | 75.7% | – |
| AA Intelligence Index v5.0 | Artificial Analysis | 54.2 | 59.4 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 56 | – |
| AA Progress Index v1 | Artificial Analysis | 350.5 | 351.6 |
| Vals Index | Vals AI | 70.8† | 70.4 |
| Vals Finance Index | Vals AI | 64.5%† | 66.3% |
| Vals Science Index | Vals AI | 59.1%† | – |
| Vals Router Index | Vals AI | 69.0%† | – |
Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.
What changed
- 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.
- Claude Sonnet 5.5 (max): 1 new result (ARC-AGI-1); 1 score revision.
- Claude Sonnet 5.5 (max): 2 new results (LMCA, DTBench).
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 2 new results (Chess Puzzles, GDP.pdf); 1 score revision.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 3 new results (FrontierCode 1.1 (AA), Terminal-Bench-Science 0.1 (AA), AA-3D).
- Claude Sonnet 5.5 (max): 2 score revisions.
Related comparisons
- Claude Sonnet 5.5 vs Claude Opus 5.5
- Claude Sonnet 5.5 vs GPT-6 Astra
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- Gemini 4 Carbon vs Claude Opus 5.5
- Gemini 4 Carbon vs GPT-6 Astra
- Gemini 4 Carbon vs GPT-6.1 Sol
- Gemini 4 Carbon vs Claude Fable 5.1
- Claude Sonnet 5.5 vs Gemini 4 Argon
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Sonnet 5.5 vs Gemini 4 Carbon: questions
- Is Claude Sonnet 5.5 better than Gemini 4 Carbon?
- Claude Sonnet 5.5 (max) and Gemini 4 Carbon (high) are neck and neck on quality (64.9 vs 65.1, within the ±6.8 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 29 Oct 2026, so check the category scores for your use.
- Claude Sonnet 5.5 vs Gemini 4 Carbon: which is cheaper, and will that change?
- Claude Sonnet 5.5 is cheaper today: $4.00 against $8.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Claude Sonnet 5.5 or Gemini 4 Carbon better for coding?
- They are level in coding (71 vs 72 on the category index). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 41.7% for Claude Sonnet 5.5 against 40.6% for Gemini 4 Carbon.
- Which is faster, Claude Sonnet 5.5 or Gemini 4 Carbon?
- Claude Sonnet 5.5 streams faster (137 vs 100 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Claude Sonnet 5.5 scores higher on long-context benchmarks (66 vs 65). Both accept 1,000,000 tokens of context.
More questions (3)
- Which has lower latency?
- Gemini 4 Carbon answers first: 103.1 s against 448.1 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on Claude Sonnet 5.5 vs Gemini 4 Carbon?
- Across the 17 benchmarks both have, Claude Sonnet 5.5 leads 3, Gemini 4 Carbon leads 14. Independent sources split: Claude Sonnet 5.5 leads on Vals Index; Gemini 4 Carbon leads on AA Intelligence Index v5.0.
- When was Gemini 4 Carbon released?
- Gemini 4 Carbon was released on 28 Oct 2026.