Claude Opus 4.5 vs Gemini 4 Carbon
Full profiles: Claude Opus 4.5 (Anthropic) and Gemini 4 Carbon (Google): every benchmark, price and rank.
Updated · Data from 9 sources
As of 29 Oct 2026, Gemini 4 Carbon is ahead of Claude Opus 4.5 on quality (65.1 vs 59.6 on the BenchLeader Index), and Gemini 4 Carbon is 1.3× cheaper at $8.00 vs $10.00 per 1M tokens blended. Gemini 4 Carbon leads in every category we measure both in. Gemini 4 Carbon streams ~1.5× faster.
Key facts (as of 29 Oct 2026)
- Claude Opus 4.5 scores 59.6 on the BenchLeader Index and Gemini 4 Carbon scores 65.1 (BenchLeader, 29 Oct 2026).
- Claude Opus 4.5 costs $10.00 per 1M tokens blended (list price, 29 Oct 2026).
- Gemini 4 Carbon costs $8.00 per 1M tokens blended (list price, 29 Oct 2026).
- Gemini 4 Carbon streams ~1.5× faster than Claude Opus 4.5 (Artificial Analysis, 7-day median, 29 Oct 2026).
- Of the 5 benchmarks both models have, Gemini 4 Carbon leads 5 (BenchLeader, 29 Oct 2026).
Claude Opus 4.5 benchmarks thinking 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 | Gemini 4 Carbon | 72 vs 61 category score; Vibe Code Bench v1.1 89.1% vs 20.6% | High |
| Reasoning | Gemini 4 Carbon | 79 vs 57 category score; Humanity's Last Exam (AA) 60.4% vs 30.1% | High |
| Knowledge | Gemini 4 Carbon | 76 vs 58 category score | High |
| Long documents | Gemini 4 Carbon | 65 vs 63 category score; AA-LCR v1.1 79.3% vs 77.3% | Medium |
| Lowest cost | Gemini 4 Carbon | $8.00 vs $10.00 per 1M blended; agentic coding session $0.320 vs $0.400 | – |
| Fastest first answer | Claude Opus 4.5 | 17.7 s (Claude Opus 4.5 (thinking)) vs 103.1 s (Gemini 4 Carbon (high)) 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
- Gemini 4 Carbon (high) leads on quality: 65.1 vs 59.6.
- Claude Opus 4.5 (thinking) is stronger in agents & tools, instruction following, maths, multimodal.
- Gemini 4 Carbon (high) is stronger in coding, knowledge, long context, reasoning.
- Gemini 4 Carbon (high) is 1.3× cheaper ($8.00 vs $10.00 per 1M blended).
- Gemini 4 Carbon (high) streams 1.6× faster (100 vs 63 tokens per second).
At a glance
| Spec | Claude Opus 4.5 | Gemini 4 Carbon |
|---|---|---|
| Developer | Anthropic | |
| Released | 24 Nov 2025 | 28 Oct 2026 |
| Context window (tokens) | 200,000 | 1,000,000 |
| Compared at | Claude Opus 4.5 (thinking) | Gemini 4 Carbon (high) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $5.00 / $25.00 / $0.500 | $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 Opus 4.5 (thinking) | Gemini 4 Carbon (high) | Leader |
|---|---|---|---|
| Reasoning | 57.4 | 78.9 | Gemini 4 Carbon |
| Coding | 60.5 | 71.7 | Gemini 4 Carbon |
| Agents & tools | 74.7 | – | not comparable |
| Maths | 64.0 | – | not comparable |
| Knowledge | 58.1 | 75.8 | Gemini 4 Carbon |
| Instruction following | 53.0 | – | not comparable |
| Multimodal | 57.1 | – | not comparable |
| Long context | 63.4 | 64.5 | Gemini 4 Carbon |
Where sources disagree
Across the 5 benchmarks both have, Claude Opus 4.5 leads 0, Gemini 4 Carbon leads 5. Every overall index that rates both puts Gemini 4 Carbon ahead.
| Overall index | Claude Opus 4.5 (thinking) | Gemini 4 Carbon (high) | Leader |
|---|---|---|---|
| BenchLeader Index | 59.6 | 65.1 | Gemini 4 Carbon |
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 Opus 4.5 (thinking) | Gemini 4 Carbon (high) |
|---|---|---|
| Blended price per 1M tokens | $10.00 | $8.00 |
| Input / output per 1M | $5.00 / $25.00 | $4.00 / $20.00 |
| Cached input per 1M | $0.500 | – |
| Price per task: chat reply | $0.0095 | $0.0076 |
| Price per task: summarize a 30-page report | $0.075 | $0.060 |
| Price per task: code edit | $0.068 | $0.054 |
| Price per task: agentic coding session | $0.400 | $0.320 |
| Price per task: structured extraction | $0.015 | $0.012 |
| Cost to run a full benchmark suite | – | $7.76 |
| Output speed | 63 tok/s | 100 tok/s |
| Time to first answer | 17.7 s | 103.1 s |
| Time to a complete answer | 25.6 s | 108.1 s |
Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.5 (thinking) scores 59.6 and takes 18 s to its first answer token; Claude Opus 4.5 (high) scores 59.1 in 1 s, Claude Opus 4.5 scores 57.9 in 1 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
126 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 Opus 4.5 (thinking) | Gemini 4 Carbon (high) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 59.6 | 65.1 |
| Agents & tools score | BenchLeader | 74.7 | – |
| Coding score | BenchLeader | 60.5 | 71.7 |
| Instruction following score | BenchLeader | 53.0 | – |
| Knowledge score | BenchLeader | 58.1 | 75.8 |
| Long context score | BenchLeader | 63.4 | 64.5 |
| Maths score | BenchLeader | 64.0 | – |
| Multimodal score | BenchLeader | 57.1 | – |
| Reasoning score | BenchLeader | 57.4 | 78.9 |
| Blended price $/M | BenchLeader | $10.00 | $8.00 |
| Output speed | BenchLeader | 63 tok/s | 100 tok/s |
| Time to first answer | BenchLeader | 17.7 s | 103.1 s |
| Context window | BenchLeader | 200,000 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 86.0%† | – |
| Humanity's Last Exam | Scale AI / CAIS | 25.2%† | – |
| SimpleBench | SimpleBench | 62.0%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1498† | – |
| LiveBench 1.0 Reasoning | LiveBench | 80.1%† | – |
| GPQA Diamond (AA) | Artificial Analysis | 86.6% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 30.1% | 60.4% |
| HLE-Diamond (AA) | Artificial Analysis | – | 69.1% |
| GPQA Diamond (Vals) | Vals AI | 85.9% | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 80.2% | – |
| ARC-AGI-1 | ARC Prize | 80.0% | – |
| ARC-AGI-2 | ARC Prize | 37.6% | – |
| CritPt | Artificial Analysis | 4.6% | 36.0% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 63.0% |
| SciPredict | Scale AI SEAL | 23.1%† | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 14.0%† | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 22.0%† | – |
| CL-bench | Epoch AI Benchmarking Hub | 21.1%† | – |
| LMCA | Epoch AI Benchmarking Hub | 44.5%† | – |
| DTBench | Epoch AI Benchmarking Hub | 89.9%† | – |
| ForecastBench | ForecastBench | 64.9%† | – |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 76.7%† | – |
| SciCode | SciCode | – | 64.2% |
| WeirdML | WeirdML | 63.7%† | – |
| GSO-Bench | GSO-Bench | 26.5%† | – |
Show all 126 benchmarks
| Metric | Publisher | Claude Opus 4.5 (thinking) | Gemini 4 Carbon (high) |
|---|---|---|---|
| Coding | |||
| Arena Coding | Arena (LMArena) | 1523† | – |
| Arena WebDev | Arena (LMArena) | 1469† | – |
| LiveBench 1.0 Coding | LiveBench | 79.7%† | – |
| LiveCodeBench | Vals AI | 83.7% | – |
| SWE-bench (Vals) | Vals AI | 76.4% | – |
| SWE-Bench Pro | Scale AI SEAL | 45.9%† | – |
| SWE-bench Verified (bash only) | SWE-bench | 76.8%† | – |
| SWE-bench Verified (any scaffold) | SWE-bench | 79.2%† | – |
| Vibe Code Bench v1.1 | Vals AI | 20.6% | 89.1% |
| SWE-Bench Pro (private) | Scale AI SEAL | 45.9%† | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1025.4† | – |
| AlgoTune | AlgoTune | 1.8† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 65.2% |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 48.5% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 40.6% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 63.1%† | – |
| GDPval | OpenAI | 45.5%† | – |
| Cybench | Cybench | 82.0%† | – |
| Remote Labor Index | Scale AI / CAIS | 3.8%† | – |
| LiveBench Agentic Coding | LiveBench | 39.7%† | – |
| Terminal-Bench Hard | Artificial Analysis | 47.0% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 89.5% | – |
| MCP Atlas | Scale AI SEAL | 69.8%† | – |
| BFCL Overall | Berkeley Function Calling Leaderboard | 77.5%† | – |
| τ²-bench | τ²-bench | 85.3%† | – |
| τ³-bench Banking | τ²-bench | 24.7%† | – |
| Finance Agent v2.1 | Vals AI | – | 67.2% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 17.5% |
| Legal Research Bench | Vals AI | – | 55.8% |
| Poker Agent | Vals AI | 1033.4%† | – |
| Tax Agent Bench | Vals AI | – | 48.9% |
| Terminal-Bench 2.0 (Vals) | Vals AI | 53.9% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 63.1% |
| BALROG | BALROG | 43.0%† | – |
| DeepResearch Bench | DeepResearch Bench | 54.8%† | – |
| METR Time Horizons | METR | 75.0%† | – |
| Vending-Bench 2 | Andon Labs | 4967.1† | 16484.2† |
| AutomationBench | Artificial Analysis | – | 77.8% |
| GDP.pdf (AA) | Artificial Analysis | – | 28.4% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1609 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 64.8% |
| DeepSearchQA | 24.0% | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 34.4%† | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 4.9%† | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 86.1%† | – |
| ProofBench | Vals AI | 36.0%† | – |
| LiveBench Mathematics | LiveBench | 90.4%† | – |
| AIME (Vals) | Vals AI | 95.4% | – |
| MGSM | Vals AI | 95.2% | – |
| Arena Maths | Arena (LMArena) | 1463† | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 45.7%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 74.4%† | – |
| AA-Omniscience v1.1 | Artificial Analysis | – | 53.5 |
| MMLU-Pro | Vals AI | 87.3% | – |
| LegalBench | Vals AI | 84.6% | – |
| CorpFin | Vals AI | 65.1% | – |
| TaxEval | Vals AI | 74.9% | – |
| MedQA | Vals AI | 95.9% | – |
| PRBench Finance | Scale AI SEAL | 46.2% | – |
| PRBench Legal | Scale AI SEAL | 44.2% | – |
| MultiNRC | Scale AI SEAL | 48.6% | – |
| CaseLaw v2 | Vals AI | 62.6% | – |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 76.5% |
| MedCode | Vals AI | 49.2% | – |
| MedScribe | Vals AI | 85.3% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 14.3%† | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 58.3% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 88.6% |
| Global-MMLU-Lite (AA) | Artificial Analysis | 91.3% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 81.3%† | – |
| LiveBench Instruction Following | LiveBench | 62.5%† | – |
| IFBench | Artificial Analysis | 58.0% | – |
| MultiChallenge | Scale AI SEAL | 59.0% | – |
| TutorBench | Scale AI SEAL | 51.2% | – |
| Arena Instruction Following | Arena (LMArena) | 1474† | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1470† | – |
| Arena Creative Writing | Arena (LMArena) | 1462† | – |
| Arena Multi-turn | Arena (LMArena) | 1484† | – |
| Arena Longer Queries | Arena (LMArena) | 1492† | – |
| Multimodal | |||
| MMMU-Pro | Artificial Analysis | 74.0% | – |
| VISTA | Scale AI SEAL | 46.4% | – |
| MMMU (validation) | MMMU | 80.7%† | – |
| MMMU-Pro (official) | MMMU | 73.9%† | – |
| MMMU-Pro (Vals) | Vals AI | 83.0% | – |
| MortgageTax | Vals AI | 67.7% | – |
| GeoBench | GeoBench | 75.0%† | – |
| VPCT | Epoch AI Benchmarking Hub | 40.0%† | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 58.6%† |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 77.3% | 79.3% |
| Arena Document | Arena (LMArena) | 1465† | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 150.1† | – |
| LiveBench 1.0 | LiveBench | 72.6%† | – |
| AA Intelligence Index v5.0 | Artificial Analysis | – | 59.4 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 29.1 | – |
| AA Progress Index v1 | Artificial Analysis | 284.4 | 351.6 |
| Vals Index | Vals AI | – | 70.4 |
| Vals Finance Index | Vals AI | – | 66.3% |
| Vals RSI Index | Vals AI | 14.8%† | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 9.6% | – |
| MASK | Scale AI SEAL | 92.5% | – |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 11.1 | – |
Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.
What changed
- Claude Opus 4.5 (thinking): BenchLeader Index 60.2 → 59.7.
- Claude Opus 4.5 (thinking): 1 new result (AA Progress Index v1).
- Claude Opus 4.5 (thinking): 1 new result (Global-MMLU-Lite (AA)).
- Claude Opus 4.5 (thinking): 1 new result (PRBench Legal).
- Claude Opus 4.5 (thinking): 2 new results (PRBench Legal, MultiNRC).
- Claude Opus 4.5 (thinking): 1 new result (PRBench Finance).
- Claude Opus 4.5 (thinking): BenchLeader Index 60.7 → 60.2.
- Claude Opus 4.5 (thinking): 1 new result (PRBench Finance).
- Claude Opus 4.5 (thinking): 1 new result (TutorBench).
- Claude Opus 4.5 (thinking): 1 new result (PRBench Finance).
Related comparisons
- Claude Opus 4.5 vs Claude Opus 5.5
- Claude Opus 4.5 vs GPT-6 Astra
- Claude Opus 4.5 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 Opus 4.5 vs Gemini 4 Argon
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Opus 4.5 vs Gemini 4 Carbon: questions
- Is Gemini 4 Carbon better than Claude Opus 4.5?
- Gemini 4 Carbon (high) leads on quality: 65.1 vs 59.6. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Carbon (high) is ahead overall as of 29 Oct 2026, but check the category scores for your use.
- Claude Opus 4.5 vs Gemini 4 Carbon: which is cheaper, and will that change?
- Gemini 4 Carbon is cheaper today: $8.00 against $10.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Claude Opus 4.5 or Gemini 4 Carbon better for coding?
- Gemini 4 Carbon scores higher in coding (72 vs 61 on the category index, where 50 is average).
- Which is faster, Claude Opus 4.5 or Gemini 4 Carbon?
- Gemini 4 Carbon streams ~1.5× faster (100 vs 63 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Gemini 4 Carbon scores higher on long-context benchmarks (65 vs 63). Gemini 4 Carbon accepts more context: 1,000,000 against 200,000 tokens for Claude Opus 4.5.
More questions (3)
- Which has lower latency?
- Claude Opus 4.5 answers first: 17.7 s against 103.1 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 Opus 4.5 vs Gemini 4 Carbon?
- Across the 5 benchmarks both have, Claude Opus 4.5 leads 0, Gemini 4 Carbon leads 5. Every overall index that rates both puts Gemini 4 Carbon ahead.
- When was Gemini 4 Carbon released?
- Gemini 4 Carbon was released on 28 Oct 2026.