Claude Fable 5.1 vs Gemini 3 Flash
Full profiles: Claude Fable 5.1 (Anthropic) and Gemini 3 Flash (Google): every benchmark, price and rank.
Updated · Data from 9 sources
As of 29 Oct 2026, Claude Fable 5.1 is ahead of Gemini 3 Flash on quality (67.0 vs 59.0 on the BenchLeader Index), but Gemini 3 Flash is 18× cheaper at $1.13 vs $20.00 per 1M tokens blended. Claude Fable 5.1 leads in every category we measure both in. Gemini 3 Flash streams 3×+ faster.
Key facts (as of 29 Oct 2026)
- Claude Fable 5.1 scores 67.0 on the BenchLeader Index and Gemini 3 Flash scores 59.0 (BenchLeader, 29 Oct 2026).
- Claude Fable 5.1 costs $20.00 per 1M tokens blended (list price, 29 Oct 2026).
- Gemini 3 Flash costs $1.13 per 1M tokens blended (list price, 29 Oct 2026).
- Gemini 3 Flash streams 3×+ faster than Claude Fable 5.1 (Artificial Analysis, 7-day median, 29 Oct 2026).
- Of the 6 benchmarks both models have, Claude Fable 5.1 leads 6 (BenchLeader, 29 Oct 2026).
Claude Fable 5.1 benchmarks max Anthropic
Gemini 3 Flash benchmarks thinking 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 |
|---|---|---|---|
| Agents & tool use | Claude Fable 5.1 | 61 vs 55 category score; τ³-Banking (AA) 47.2% vs 20.8% | Medium |
| Long documents | Claude Fable 5.1 | 68 vs 64 category score; AA-LCR v1.1 85.3% vs 78.0% | Medium |
| Images and other media | Claude Fable 5.1 | 67 vs 63 category score | Medium |
| Chat quality (human preference) | – | Only Claude Fable 5.1 has an Arena rating (70 category score) | Not comparable |
| Lowest cost | Gemini 3 Flash | $1.13 vs $20.00 per 1M blended; agentic coding session $0.042 vs $0.800 | – |
| Fastest first answer | Gemini 3 Flash | 6.0 s (Gemini 3 Flash (thinking)) vs 179.6 s (Claude Fable 5.1 (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 Fable 5.1 (max) leads on quality: 67.0 vs 59.0.
- Claude Fable 5.1 (max) is stronger in agents & tools, coding, human preference, knowledge, long context, maths, multimodal, reasoning.
- Gemini 3 Flash (thinking) is stronger in instruction following.
- Gemini 3 Flash (thinking) is 18× cheaper ($1.13 vs $20.00 per 1M blended).
- Gemini 3 Flash (thinking) streams 3.2× faster (209 vs 66 tokens per second).
At a glance
| Spec | Claude Fable 5.1 | Gemini 3 Flash |
|---|---|---|
| Developer | Anthropic | |
| Released | 1 Sept 2026 | 17 Dec 2025 |
| Context window (tokens) | 1,000,000 | 1,048,576 |
| Compared at | Claude Fable 5.1 (max) | Gemini 3 Flash (thinking) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $10.00 / $50.00 / $0.250 | $0.500 / $3.00 / $0.050 |
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 5.1 (max) | Gemini 3 Flash (thinking) | Leader |
|---|---|---|---|
| Reasoning | 70.8 | – | not comparable |
| Coding | 70.7 | – | not comparable |
| Agents & tools | 60.5 | 55.1 | Claude Fable 5.1 |
| Maths | 72.6 | – | not comparable |
| Knowledge | 72.9 | – | not comparable |
| Instruction following | – | 75.8 | not comparable |
| Human preference | 69.9 | – | not comparable |
| Multimodal | 67.1 | 62.7 | Claude Fable 5.1 |
| Long context | 67.6 | 63.8 | Claude Fable 5.1 |
Where sources disagree
Across the 6 benchmarks both have, Claude Fable 5.1 leads 6, Gemini 3 Flash leads 0. Every overall index that rates both puts Claude Fable 5.1 ahead.
| Overall index | Claude Fable 5.1 (max) | Gemini 3 Flash (thinking) | Leader |
|---|---|---|---|
| BenchLeader Index | 67.0 | 59.0 | Claude Fable 5.1 |
| Arena Text | 1503 | 1458† | Claude Fable 5.1 |
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 Fable 5.1 (max) | Gemini 3 Flash (thinking) |
|---|---|---|
| Blended price per 1M tokens | $20.00 | $1.13 |
| Input / output per 1M | $10.00 / $50.00 | $0.500 / $3.00 |
| Cached input per 1M | $0.250 | $0.050 |
| Price per task: chat reply | $0.019 | $0.0011 |
| Price per task: summarize a 30-page report | $0.150 | $0.0078 |
| Price per task: code edit | $0.135 | $0.0075 |
| Price per task: agentic coding session | $0.800 | $0.042 |
| Price per task: structured extraction | $0.030 | $0.0016 |
| Cost to run a full benchmark suite | $12.99 | – |
| Output speed | 66 tok/s | 209 tok/s |
| Time to first answer | 179.6 s | 6.0 s |
| Time to a complete answer | 187.2 s | 8.4 s |
Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5.1 (max) scores 67.0 and takes 180 s to its first answer token; Claude Fable 5.1 scores 66.4 in 3 s, Claude Fable 5.1 (xhigh) scores 64.9 in 58 s. Gemini 3 Flash (thinking) scores 59.0 and takes 6 s to its first answer token; Gemini 3 Flash (high) scores 58.3 in 1 s, Gemini 3 Flash scores 57.0 in 1 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
169 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 5.1 (max) | Gemini 3 Flash (thinking) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 67.0 | 59.0 |
| Agents & tools score | BenchLeader | 60.5 | 55.1 |
| Coding score | BenchLeader | 70.7 | – |
| Human preference score | BenchLeader | 69.9 | – |
| Knowledge score | BenchLeader | 72.9 | – |
| Long context score | BenchLeader | 67.6 | 63.8 |
| Maths score | BenchLeader | 72.6 | – |
| Multimodal score | BenchLeader | 67.1 | 62.7 |
| Reasoning score | BenchLeader | 70.8 | – |
| Instruction following score | BenchLeader | – | 75.8 |
| Blended price $/M | BenchLeader | $20.00 | $1.13 |
| Output speed | BenchLeader | 66 tok/s | 209 tok/s |
| Time to first answer | BenchLeader | 179.6 s | 6.0 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 83.2%† |
| Humanity's Last Exam | Scale AI / CAIS | 46.5%† | – |
| SimpleBench | SimpleBench | – | 61.1%† |
| Arena Hard Prompts | Arena (LMArena) | 1523 | 1493† |
| LiveBench 2.0 Reasoning | LiveBench | 91.7%† | – |
| LiveBench 1.0 Reasoning | LiveBench | 91.7% | – |
| GPQA Diamond (AA) | Artificial Analysis | 93.7% | 89.8% |
| Humanity's Last Exam (AA) | Artificial Analysis | 59.1% | 36.6% |
| HLE-Diamond (AA) | Artificial Analysis | 60.1% | – |
| GPQA Diamond (Vals) | Vals AI | 93.4%† | 87.9%† |
| ARC-AGI-1 | ARC Prize | 97.5% | 84.7%† |
| ARC-AGI-2 | ARC Prize | 90.0% | 33.6%† |
| CritPt | Artificial Analysis | 29.7% | 8.6% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 51.0% | – |
| MysteryMechanism | Vals AI | 47.8%† | – |
| SciPredict | Scale AI SEAL | – | 22.2%† |
| Chess Puzzles | Epoch AI Benchmarking Hub | 48.0% | 39.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 58.0% | 20.0%† |
| LMCA | Epoch AI Benchmarking Hub | 65.5%† | 43.1%† |
| DTBench | Epoch AI Benchmarking Hub | 97.6%† | 89.1%† |
| ForecastBench | ForecastBench | – | 64.7%† |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 75.4%† |
| SciCode | SciCode | 63.1% | – |
| WeirdML | WeirdML | 92.9% | 61.6%† |
| FrontierCode | Cognition | 50.9%† | – |
Show all 169 benchmarks
| Metric | Publisher | Claude Fable 5.1 (max) | Gemini 3 Flash (thinking) |
|---|---|---|---|
| Coding | |||
| GSO-Bench | GSO-Bench | 88.2%† | 9.8%† |
| Arena Coding | Arena (LMArena) | 1538 | 1506† |
| Arena WebDev | Arena (LMArena) | 1745 | 1440† |
| LiveBench 2.0 Coding | LiveBench | 97.7%† | – |
| LiveBench 1.0 Coding | LiveBench | 86.4% | – |
| LiveCodeBench | Vals AI | 90.5%† | 85.6%† |
| IOI | Vals AI | 90.8%† | – |
| SWE-bench (Vals) | Vals AI | – | 75.0%† |
| SWE-Bench Pro | Scale AI SEAL | – | 34.6%† |
| SWE-bench Verified (bash only) | SWE-bench | – | 75.8%† |
| SWE-bench Verified (any scaffold) | SWE-bench | – | 75.8%† |
| Code Migration | Vals AI | 54.6%† | 6.4%† |
| ProgramBench | Vals AI | 7.0%† | 0.0%† |
| SWE-bench Multimodal | Vals AI | 61.3%† | – |
| Vibe Code Bench 1-100 | Vals AI | 28.0%† | – |
| Vibe Code Bench v1.1 | Vals AI | 90.3%† | 20.2%† |
| SWE-Bench Pro (private) | Scale AI SEAL | – | 34.6%† |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 60.0%† | 8.2%† |
| SWE Atlas: Refactoring | Scale AI SEAL | 56.7%† | 10.0%† |
| SWE Atlas: Test Writing | Scale AI SEAL | 67.0%† | 30.3%† |
| MirrorCode | Epoch AI Benchmarking Hub | 73.3%† | – |
| CursorBench | Cursor | 51.8% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 2143.2† | 1367.2† |
| FrontierSWE | Epoch AI Benchmarking Hub | 56.3% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 52.0% | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 91.4% | – |
| Startrise Frontend | Startrise | 77.1%† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 49.0% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 31.6% | – |
| LiveCodeBench (AA) | Artificial Analysis | – | 90.8% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 57.9% | 64.3%† |
| Remote Labor Index | Scale AI / CAIS | 17.9%† | – |
| APEX-Agents | Mercor | 68.6%† | – |
| Arena Agent | Arena (LMArena) | 13.9 | – |
| LiveBench Long Agentic | LiveBench | 77.9%† | – |
| LiveBench Browser | LiveBench | 89.8%† | – |
| LiveBench Agentic Coding | LiveBench | 66.1% | – |
| Terminal-Bench Hard | Artificial Analysis | – | 38.6% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 80.4% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 85.0%† | 53.9%† |
| MCP Atlas | Scale AI SEAL | 87.2%† | 62.0%† |
| HiL-Bench | Scale AI SEAL | 61.5%† | – |
| τ²-bench | τ²-bench | – | 83.5%† |
| τ³-bench Banking | τ²-bench | – | 27.3%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 62.7% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1764 | – |
| τ³-Banking (AA) | Artificial Analysis | 47.2% | 20.8% |
| ITBench SRE (AA) | Artificial Analysis | 49.5% | – |
| Analyst Agent (AA) | Artificial Analysis | 57.5% | – |
| APEX-Agents (AA) | Artificial Analysis | – | 27.7% |
| CUA-bench | Vals AI | 13.2% | – |
| CyberBench | Vals AI | 70.4%† | – |
| Finance Agent v2 | Vals AI | 58.9%† | 42.5%† |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 6.7%† | 0.0%† |
| Legal Research Bench | Vals AI | 55.3%† | 18.3%† |
| Poker Agent | Vals AI | – | 1100.2%† |
| Robo-bench | Vals AI | 5.8% | – |
| SkillsBench | Vals AI | 61.5%† | – |
| SREBench | Vals AI | 22.9%† | – |
| Tax Agent Bench | Vals AI | 49.2%† | 11.8%† |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 51.7%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 58.1%† | – |
| Terminal-Bench Science | Vals AI | 40.0%† | – |
| Time Horizon Index: KSP | Vals AI | 63.3%† | – |
| Arena Search | Arena (LMArena) | 1233† | – |
| BALROG | BALROG | – | 48.1%† |
| DeepResearch Bench | DeepResearch Bench | – | 47.9%† |
| Vending-Bench 2 | Andon Labs | 5421.6† | 3634.7† |
| AutomationBench | Artificial Analysis | 59.4% | – |
| GDP.pdf (AA) | Artificial Analysis | 26.2% | – |
| Harvey LAB-AA v1.1 | Harvey | 6.4% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1669 | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 43.3% | – |
| CWE-Bench (AA) | Artificial Analysis | 50.8% | – |
| DeepSec-Bench (AA) | Artificial Analysis | 23.5% | – |
| CyberGym end-to-end (AA) | Artificial Analysis | 0.8% | – |
| BrowseComp | OpenAI | – | 16.9%† |
| FACTS Search | – | 80.9%† | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 90.2% | 51.2%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 87.8% | 17.1%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | 92.8%† |
| ProofBench | Vals AI | 100.0% | 15.0%† |
| LiveBench Mathematics | LiveBench | 97.0% | – |
| AIME (Vals) | Vals AI | – | 95.6%† |
| MGSM | Vals AI | – | 93.3%† |
| AIME 2026 | MathArena | – | 96.7%† |
| HMMT February 2026 | MathArena | – | 89.4%† |
| MathArena Apex | MathArena | – | 15.6%† |
| Arena Maths | Arena (LMArena) | 1529 | 1475† |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 70.8% | 66.8%† |
| LiveBench 2.0 Data Analysis | LiveBench | 80.3%† | – |
| LiveBench Research | LiveBench | 82.0%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 80.3% | – |
| AA-Omniscience v1.1 | Artificial Analysis | 46.3 | – |
| MMLU-Pro | Vals AI | 92.4%† | 88.6%† |
| LegalBench | Vals AI | 88.5%† | 86.9%† |
| CorpFin | Vals AI | – | 66.4%† |
| TaxEval | Vals AI | 76.0%† | 73.9%† |
| MedQA | Vals AI | – | 95.8%† |
| PRBench Finance | Scale AI SEAL | 50.8%† | – |
| PRBench Legal | Scale AI SEAL | 51.6%† | – |
| CaseLaw v2 | Vals AI | – | 55.8%† |
| Excel Modeling Benchmark | Vals AI | 76.7%† | 26.0%† |
| Excel Modeling Benchmark v1.1 | Vals AI | 76.7%† | – |
| MedCode | Vals AI | 53.5%† | 55.9%† |
| MedScribe | Vals AI | 91.3%† | 69.9%† |
| Public Benefits Bench v1.1 | Vals AI | 74.9%† | – |
| EBR-bench | Epoch AI Benchmarking Hub | 57.1% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 27.6% | 10.0%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 68.4% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 30.0% | – |
| Global-MMLU-Lite (AA) | Artificial Analysis | – | 92.8%† |
| HealthBench Professional (AA) | OpenAI | 57.8% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 89.5% | – |
| LiveBench Instruction Following | LiveBench | 73.0% | – |
| IFBench | Artificial Analysis | – | 78.0% |
| Arena Instruction Following | Arena (LMArena) | 1501 | 1458† |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1503 | 1473† |
| Arena Creative Writing | Arena (LMArena) | 1487 | 1457† |
| Arena Multi-turn | Arena (LMArena) | 1488 | 1482† |
| Arena Longer Queries | Arena (LMArena) | 1511 | 1476† |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1320 | 1285† |
| LiveBench Design | LiveBench | 83.4%† | – |
| MMMU-Pro | Artificial Analysis | – | 79.9% |
| MMMU-Pro (Vals) | Vals AI | 90.6%† | 87.6%† |
| MortgageTax | Vals AI | 70.8%† | 68.7%† |
| GeoBench | GeoBench | – | 88.0%† |
| VPCT | Epoch AI Benchmarking Hub | – | 72.6%† |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 41.9%† | 0.0%† |
| Code2Video-AA | Artificial Analysis | 1325 | – |
| AA-3D | Artificial Analysis | 1135 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 85.3% | 78.0% |
| Arena Document | Arena (LMArena) | 1493 | 1439† |
| MLCR | Artificial Analysis | 15.6% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 166.5† | 151.9† |
| LiveBench 2.0 | LiveBench | 85.7%† | – |
| LiveBench 1.0 | LiveBench | 83.4% | – |
| AA Intelligence Index v5.0 | Artificial Analysis | 49.0 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 53.4 | 26.3 |
| AA Progress Index v1 | Artificial Analysis | 340.8 | 290.1 |
| Vals RSI Index | Vals AI | 36.1% | – |
| Vals Multimodal Index | Vals AI | – | 52.2%† |
| AA Cyber Index | Artificial Analysis | 25.0 | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 13.7%† | – |
Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.
What changed
- Claude Fable 5.1 (max): BenchLeader Index 67.9 → 67.1.
- Gemini 3 Flash (thinking): BenchLeader Index 60.1 → 59.0.
- Claude Fable 5.1 (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $7.63/M to $13.04/M (71% up).
- Gemini 3 Flash (thinking): 1 new result (AA Progress Index v1).
- Claude Fable 5.1 (max): 2 new results (Robo-bench, Vals RSI Index).
- Claude Fable 5.1 (max): 1 score revision.
- Claude Fable 5.1 (max): 1 score revision.
- Gemini 3 Flash (thinking): 2 new results (AA-Omniscience v1.1: accuracy, AA-Omniscience v1.1: non-hallucination).
- Claude Fable 5.1 (max): 2 score revisions.
- Claude Fable 5.1 (max): 1 score revision.
Related comparisons
- Claude Fable 5.1 vs Claude Opus 5.5
- Claude Fable 5.1 vs GPT-6 Astra
- Claude Fable 5.1 vs GPT-6.1 Sol
- Gemini 3 Flash vs Claude Opus 5.5
- Gemini 3 Flash vs GPT-6 Astra
- Gemini 3 Flash vs GPT-6.1 Sol
- Claude Opus 5 vs Gemini 3 Flash
- Claude Fable 5.1 vs Gemini 3 Pro
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Fable 5.1 vs Gemini 3 Flash: questions
- Is Claude Fable 5.1 better than Gemini 3 Flash?
- Claude Fable 5.1 (max) leads on quality: 67.0 vs 59.0. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.1 (max) is ahead overall as of 29 Oct 2026, but check the category scores for your use.
- Claude Fable 5.1 vs Gemini 3 Flash: which is cheaper, and will that change?
- Gemini 3 Flash is cheaper today: $1.13 against $20.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Which is faster, Claude Fable 5.1 or Gemini 3 Flash?
- Gemini 3 Flash streams 3×+ faster (209 vs 66 output tokens per second, Artificial Analysis 7-day median).
- Is Claude Fable 5.1 or Gemini 3 Flash better for agents and tool use?
- Claude Fable 5.1 scores higher in agentic tasks (61 vs 55 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 47.2% for Claude Fable 5.1 against 20.8% for Gemini 3 Flash.
- Which is better for long documents?
- Claude Fable 5.1 scores higher on long-context benchmarks (68 vs 64). Both take about 1M tokens: Claude Fable 5.1 1,000,000, Gemini 3 Flash 1,048,576.
More questions (3)
- Which has lower latency?
- Gemini 3 Flash answers first: 6.0 s against 179.6 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 Fable 5.1 vs Gemini 3 Flash?
- Across the 6 benchmarks both have, Claude Fable 5.1 leads 6, Gemini 3 Flash leads 0. Every overall index that rates both puts Claude Fable 5.1 ahead.
- When was Claude Fable 5.1 released?
- Claude Fable 5.1 was released on 1 Sept 2026.