Claude Fable 5 vs Gemini 3 Pro
Full profiles: Claude Fable 5 (Anthropic) and Gemini 3 Pro (Google): every benchmark, price and rank.
Updated · Data from 17 sources
As of 12 Nov 2026, Claude Fable 5 is ahead of Gemini 3 Pro on quality (66.3 vs 60.1 on the BenchLeader Index). Claude Fable 5 leads in every category we measure both in.
Key facts (as of 12 Nov 2026)
- Claude Fable 5 scores 66.3 on the BenchLeader Index and Gemini 3 Pro scores 60.1 (BenchLeader, 12 Nov 2026).
- Claude Fable 5 costs $20.00 per 1M tokens blended (list price, 12 Nov 2026).
- Of the 12 benchmarks both models have, Claude Fable 5 leads 11 (BenchLeader, 12 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 Fable 5 | 71 vs 58 category score; LiveCodeBench 89.8% vs 86.4% | High |
| Agents & tool use | Either | 62 vs 62 category score; MCP Atlas 83.3% vs 70.3% | Either |
| Reasoning | Claude Fable 5 | 80 vs 64 category score; Kagi LLM Benchmark 88.8% vs 80.1% | High |
| Knowledge | Claude Fable 5 | 67 vs 56 category score; MMLU-Pro 91.5% vs 90.1% | High |
| Chat quality (human preference) | Either | 68 vs 68 on Arena votes | Either |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Claude Fable 5 leads on quality: 66.3 vs 60.1.
- Claude Fable 5 is stronger in agents & tools, coding, knowledge, reasoning.
At a glance
| Spec | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| Developer | Anthropic | |
| Released | 9 Jun 2026 | 18 Nov 2025 |
| Context window (tokens) | 1,000,000 | – |
| Compared at | Claude Fable 5 | Gemini 3 Pro |
| Open weights | No | No |
| Price in / out / cached input per 1M | $10.00 / $50.00 / $1.00 | – |
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 Fable 5 | Gemini 3 Pro | Leader |
|---|---|---|---|
| Reasoning | 80.1 | 64.4 | Claude Fable 5 |
| Coding | 70.5 | 57.8 | Claude Fable 5 |
| Agents & tools | 61.6 | 61.5 | level |
| Maths | – | 54.2 | not comparable |
| Knowledge | 66.7 | 56.0 | Claude Fable 5 |
| Instruction following | – | 60.1 | not comparable |
| Human preference | 67.7 | 67.7 | level |
| Multimodal | – | 65.6 | 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: Maths, Instruction following, Long context, Multimodal.
Where sources disagree
Across the 12 benchmarks both have, Claude Fable 5 leads 11, Gemini 3 Pro leads 1. Every overall index that rates both puts Claude Fable 5 ahead.
| Overall index | Claude Fable 5 | Gemini 3 Pro | Leader |
|---|---|---|---|
| BenchLeader Index | 66.3 | 60.1 | Claude Fable 5 |
| Arena Text | 1504† | 1486 | Claude Fable 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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| Blended price per 1M tokens | $20.00 | – |
| Input / output per 1M | $10.00 / $50.00 | – / – |
| Cached input per 1M | $1.00 | – |
| Price per task: chat reply | $0.019 | – |
| Price per task: summarize a 30-page report | $0.150 | – |
| Price per task: code edit | $0.135 | – |
| Price per task: agentic coding session | $0.800 | – |
| Price per task: structured extraction | $0.030 | – |
| Agentic coding session, input mostly cached | $0.395 | – |
| Output speed | 53 tok/s | – |
| Time to first answer | 3.4 s | – |
Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5 scores 66.3 and takes 3 s to its first answer token; Claude Fable 5 (max) scores 64.9 in 93 s, Claude Fable 5 (high) scores 63.9 in 3 s. Gemini 3 Pro scores 60.1; 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
163 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 Fable 5 | Gemini 3 Pro |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 66.3 | 60.1 |
| Agents & tools score | BenchLeader | 61.6 | 61.5 |
| Coding score | BenchLeader | 70.5 | 57.8 |
| Human preference score | BenchLeader | 67.7 | 67.7 |
| Knowledge score | BenchLeader | 66.7 | 56.0 |
| Reasoning score | BenchLeader | 80.1 | 64.4 |
| Instruction following score | BenchLeader | – | 60.1 |
| Maths score | BenchLeader | – | 54.2 |
| Multimodal score | BenchLeader | – | 65.6 |
| Blended price $/M | BenchLeader | $20.00 | – |
| Output speed | BenchLeader | 53 tok/s | – |
| Time to first answer | BenchLeader | 3.4 s | – |
| Context window | BenchLeader | 1,000,000 tokens | – |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 85.9%† | 92.6% |
| Humanity's Last Exam | Scale AI / CAIS | – | 37.5% |
| SimpleBench | SimpleBench | 81.9%† | 76.4% |
| Arena Hard Prompts | Arena (LMArena) | 1529† | 1502 |
| LiveBench 1.0 Reasoning | LiveBench | 89.7%† | – |
| GPQA Diamond (AA) | Artificial Analysis | 92.6%† | 90.8%† |
| Humanity's Last Exam (AA) | Artificial Analysis | 55.5%† | 39.7%† |
| GPQA Diamond (Vals) | Vals AI | 93.2% | 91.7%† |
| EnigmaEval | Scale AI SEAL | 39.3%† | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 88.8% | 80.1% |
| GPQA Diamond (HELM) | HELM Capabilities | – | 80.3% |
| ARC-AGI-1 | ARC Prize | 98.5%† | 75.0% |
| ARC-AGI-2 | ARC Prize | 89.2%† | 54.0% |
| CritPt | Artificial Analysis | 28.6%† | 9.1%† |
| SciPredict | Scale AI SEAL | – | 25.3% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 47.0%† | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 52.0%† | – |
| CL-bench | Epoch AI Benchmarking Hub | – | 15.8% |
| LMCA | Epoch AI Benchmarking Hub | 60.3%† | – |
| DTBench | Epoch AI Benchmarking Hub | 98.4%† | – |
| ForecastBench | ForecastBench | 65.9%† | 65.0% |
| BTF-3 | Epoch AI Benchmarking Hub | 13.0%† | – |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 72.9% |
| SciCode | SciCode | 61.0%† | – |
| WeirdML | WeirdML | 91.9%† | 69.9% |
Show all 163 benchmarks
| Metric | Publisher | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|---|
| Coding | |||
| FrontierCode | Cognition | 53.5% | – |
| GSO-Bench | GSO-Bench | 78.4% | 18.6% |
| Arena Coding | Arena (LMArena) | 1551† | 1517 |
| Arena WebDev | Arena (LMArena) | 1625† | 1441 |
| LiveBench 1.0 Coding | LiveBench | 86.0%† | – |
| LiveCodeBench | Vals AI | 89.8% | 86.4% |
| SWE-bench (Vals) | Vals AI | 95.0% | 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 | 55.1% | – |
| ProgramBench | Vals AI | 2.0% | – |
| Vibe Code Bench v1.1 | Vals AI | 90.3% | 14.3%† |
| SWE-Bench Pro (private) | Scale AI SEAL | – | 43.3% |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 39.0%† | – |
| SWE Atlas: Refactoring | Scale AI SEAL | 54.8%† | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 55.6%† | – |
| MirrorCode | Epoch AI Benchmarking Hub | 70.0%† | – |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 95.0%† | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 69.7%† | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 2041.3† | 1176.8 |
| AlgoTune | AlgoTune | – | 1.8 |
| FrontierSWE | Epoch AI Benchmarking Hub | 47.0%† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 42.4%† | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 84.6%† | – |
| Startrise Frontend | Startrise | 73.8% | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 65.5 | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 58.4† | – |
| Design Arena Website | Design Arena | 1290 | 1248 |
| LiveCodeBench (AA) | Artificial Analysis | – | 91.8%† |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 44.9%† | 69.4% |
| GDPval | OpenAI | – | 40.3% |
| Remote Labor Index | Scale AI / CAIS | 16.1% | 1.3% |
| APEX-Agents | Mercor | 63.6% | – |
| Arena Agent | Arena (LMArena) | 7.3† | – |
| LiveBench Agentic Coding | LiveBench | 62.2%† | – |
| Terminal-Bench Hard | Artificial Analysis | 62.9%† | 41.7%† |
| τ²-Bench Telecom (AA) | Artificial Analysis | 98.5%† | 87.1%† |
| Terminal-Bench 2.1 (Vals) | Vals AI | 80.5% | – |
| MCP Atlas | Scale AI SEAL | 83.3% | 70.3% |
| HiL-Bench | Scale AI SEAL | 56.3% | – |
| BFCL Overall | Berkeley Function Calling Leaderboard | – | 72.5% |
| τ²-bench | τ²-bench | – | 82.5%† |
| τ³-bench Banking | τ²-bench | 39.7%† | 18.0%† |
| τ³-Banking (AA) | Artificial Analysis | 38.1%† | – |
| Analyst Agent (AA) | Artificial Analysis | 48.8%† | – |
| Finance Agent v2 | Vals AI | 56.3% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 11.3% | – |
| Legal Research Bench | Vals AI | 49.5% | – |
| Poker Agent | Vals AI | – | 1078.9% |
| Tax Agent Bench | Vals AI | 38.3% | – |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 55.1%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 41.4% | – |
| Terminal-Bench Science | Vals AI | 15.7% | – |
| Web Search Index | Vals AI | 46.9% | – |
| Arena Search | Arena (LMArena) | 1229† | 1201 |
| BALROG | BALROG | – | 58.1% |
| DeepResearch Bench | DeepResearch Bench | – | 46.3%† |
| PostTrainBench | Epoch AI Benchmarking Hub | 37.3%† | – |
| METR Time Horizons | METR | – | 71.0% |
| GBAEval | Epoch AI Benchmarking Hub | 74.5% | – |
| Vending-Bench 2 | Andon Labs | 4529.9 | 5478.2 |
| AutomationBench | Artificial Analysis | 54.1%† | – |
| GDP.pdf (AA) | Artificial Analysis | 24.0%† | – |
| EnterpriseOps-Gym | Artificial Analysis | 51.1%† | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1535† | – |
| Design Arena Agentic | Design Arena | 1267 | 1073 |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 87.0%† | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 90.2%† | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 99.7%† | 91.4% |
| ProofBench | Vals AI | 95.0%† | 20.0% |
| LiveBench Mathematics | LiveBench | 96.0%† | – |
| 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) | 1521† | 1476 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 70.7%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 80.5%† | – |
| MMLU-Pro | Vals AI | 91.5% | 90.1% |
| LegalBench | Vals AI | 88.6% | 87.0%† |
| CorpFin | Vals AI | 71.8% | 63.7%† |
| TaxEval | Vals AI | 76.9% | 72.6%† |
| MedQA | Vals AI | – | 96.0%† |
| PRBench Finance | Scale AI SEAL | 53.9% | 39.2% |
| PRBench Legal | Scale AI SEAL | 52.6% | 40.6% |
| MultiNRC | Scale AI SEAL | – | 59.0% |
| MMLU-Pro (HELM) | HELM Capabilities | – | 90.3% |
| CaseLaw v2 | Vals AI | – | 53.1%† |
| Excel Modeling Benchmark | Vals AI | 73.7% | – |
| MedCode | Vals AI | 56.1% | 52.2%† |
| MedScribe | Vals AI | 88.5% | 72.0%† |
| Public Benefits Bench v1.1 | Vals AI | 70.4% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 39.5%† | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 30.0% | – |
| Global-MMLU-Lite (AA) | Artificial Analysis | – | 92.2%† |
| Instruction following | |||
| LiveBench Language | LiveBench | 90.7%† | – |
| LiveBench Instruction Following | LiveBench | 75.8%† | – |
| IFBench | Artificial Analysis | 63.5%† | 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) | 1509† | 1473 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1504† | 1486 |
| EQ-Bench 4 | EQ-Bench | 1313 | – |
| Arena Creative Writing | Arena (LMArena) | 1502† | 1484 |
| Arena Multi-turn | Arena (LMArena) | 1517† | 1496 |
| Arena Longer Queries | Arena (LMArena) | 1522† | 1491 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1326† | 1305 |
| MMMU-Pro | Artificial Analysis | – | 80.2%† |
| VISTA | Scale AI SEAL | – | 51.5% |
| MMMU-Pro (official) | MMMU | – | 81.0% |
| MMMU-Pro (Vals) | Vals AI | 89.3% | 87.5%† |
| MortgageTax | Vals AI | 68.9% | 69.1%† |
| AudioMC | Scale AI SEAL | – | 54.6%† |
| AudioMC (text output) | Scale AI SEAL | – | 54.6%† |
| VTB | Scale AI SEAL | – | 26.9% |
| GeoBench | GeoBench | 89.0%† | 84.0% |
| VPCT | Epoch AI Benchmarking Hub | – | 91.0% |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 38.6% | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.3%† | 76.0%† |
| Arena Document | Arena (LMArena) | 1500† | 1451 |
| MLCR | Artificial Analysis | 20.6%† | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 164.1 | 153.0 |
| LiveBench 1.0 | LiveBench | 83.0%† | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 49.6† | 28.0† |
| AA Progress Index v1 | Artificial Analysis | 329.3† | 290.7† |
| HELM Capabilities mean | HELM Capabilities | – | 79.9% |
| Vals RSI Index | Vals AI | 24.3%† | – |
| Vals Multimodal Index | Vals AI | 74.2% | – |
| 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 2026-11-12. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Gemini 3 Pro: 1 new result (Arena Search).
- Claude Fable 5: 1 score revision.
- Claude Fable 5: 1 score revision.
- Claude Fable 5: BenchLeader Index 67.3 → 66.5.
- Claude Fable 5: 1 score revision.
- Claude Fable 5: 1 new result (Harvey's Legal Agent Benchmark v1).
- Gemini 3 Pro: 1 score revision.
- Claude Fable 5: 1 score revision.
- Gemini 3 Pro: 1 score revision.
- Claude Fable 5: 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
Related comparisons
- Claude Fable 5 vs Claude Fable 5.2
- Claude Fable 5 vs Gemini 4 Carbon
- Claude Fable 5 vs Claude Opus 5.5
- Gemini 3 Pro vs Gemini 4 Carbon
- Gemini 3 Pro vs Claude Opus 5.5
- Gemini 3 Pro vs GPT-6 Astra
- Claude Fable 5 vs Claude Fable 5.1
- Claude Fable 5 vs GPT-6.1 Sol
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Fable 5 vs Gemini 3 Pro: questions
- Is Claude Fable 5 better than Gemini 3 Pro?
- Claude Fable 5 leads on quality: 66.3 vs 60.1. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5 is ahead overall as of 12 Nov 2026, but check the category scores for your use.
- Is Claude Fable 5 or Gemini 3 Pro better for coding?
- Claude Fable 5 scores higher in coding (71 vs 58 on the category index, where 50 is average). On LiveCodeBench, the top shared coding benchmark, it is 89.8% for Claude Fable 5 against 86.4% for Gemini 3 Pro.
- Is Claude Fable 5 or Gemini 3 Pro better for agents and tool use?
- They are level in agentic tasks (62 vs 62 on the category index). On MCP Atlas, the top shared agents & tools benchmark, it is 83.3% for Claude Fable 5 against 70.3% for Gemini 3 Pro.
- Do independent benchmarks agree on Claude Fable 5 vs Gemini 3 Pro?
- Across the 12 benchmarks both have, Claude Fable 5 leads 11, Gemini 3 Pro leads 1. Every overall index that rates both puts Claude Fable 5 ahead.
- When was Claude Fable 5 released?
- Claude Fable 5 was released on 9 Jun 2026.