Model comparison
Claude Fable 5 vs Gemini 3 Pro
Claude Fable 5 is the stronger model overall, scoring 66.3 to 54.7 on the Noometry Index.
Last verified . 39 shared benchmarks.
GoogleSummary
- They share 39 benchmarks with published results for both. Claude Fable 5 scores higher in 8 categories and Gemini 3 Pro in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.4 to 48.8.
- The biggest single-benchmark swing is ProofBench: 95% for Claude Fable 5 and 20% for Gemini 3 Pro.
Side by side
| Claude Fable 5 | Gemini 3 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 66.3 | 54.7 |
| Released | 2026-06-07 | 2025-11-18 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 61 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 67.0 (#4), Gemini 3 Pro: 52.1 (#33)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| LMArena WebDev | 1626 | 1439 |
| WeirdML | 91.9% | 69.9% |
| LMArena Coding | 1519 | 1482 |
| ALE-Bench | 2,041 | 1,177 |
| SWE-bench Verified | — | 72.9% |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| SWE-bench Verified (bash only) | — | 74.2% |
| SWE-bench Multilingual | — | 68.7% |
| FrontierSWE | 47% | — |
| SciCode | 61% | — |
| GSO | — | 18.6% |
| MirrorCode | 63.9% | — |
| AlgoTune | — | 1.83 |
Agentic & Tool Use Claude Fable 5 leads
Claude Fable 5: 54.1 (#2), Gemini 3 Pro: 40.5 (#21)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| Remote Labor Index | 16.1% | 1.3% |
| τ²-bench Banking | 39.7% | 18% |
| LMArena Search | 1230 | 1207 |
| Vending-Bench 2 | 5,680 | 5,478 |
| Terminal-Bench | — | 69.4% |
| APEX-Agents | 63.6% | — |
| Berkeley Function Calling Leaderboard | — | 72.5% |
| GDPval | — | 40.3% |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| DeepResearch Bench | — | 46.3% |
| PostTrainBench | 41.8% | — |
| BALROG | — | 58.1% |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| METR Time Horizons | — | 71% |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#4), Gemini 3 Pro: 52.5 (#28)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| ARC-AGI-2 | 89.2% | 31.1% |
| SimpleBench | 81.9% | 76.4% |
| Kagi LLM Benchmark | 91.4% | 80.1% |
| NYT Connections (extended) | 92.7% | 94.4% |
| ARC-AGI-1 | 98.5% | 75% |
| CritPt | 28.6% | 6.9% |
| Chess Puzzles | 41% | 31% |
| EnigmaEval | 39.3% | 18.2% |
| LMArena Hard Prompts | 1508 | 1481 |
| Epoch Capabilities Index | 163.6 | 152.96 |
| EBR-Bench | 39.5% | — |
| Mystery Game Puzzles | 52% | — |
| DTBench | 98.4% | — |
| LMCA | 61.1% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
| ForecastBench | — | 61.2 |
Math Claude Fable 5 leads
Claude Fable 5: 88.4 (#5), Gemini 3 Pro: 48.8 (#50)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 91.4% |
| ProofBench | 95% | 20% |
| LMArena Math | 1519 | 1475 |
| FrontierMath (Tiers 1-3) | 87% | — |
| FrontierMath Tier 4 | 90.2% | — |
| MathArena Final-Answer Competitions | — | 67% |
| Omni-MATH | — | 55.5% |
| FrontierMath (Feb 2025 set) | — | 37.6% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge Gemini 3 Pro leads
Claude Fable 5: 62.3 (#22), Gemini 3 Pro: 64.3 (#15)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 85.9% | 92.6% |
| LMArena Expert | 1534 | 1475 |
| Humanity's Last Exam | — | 37.5% |
| SimpleQA Verified | 70.7% | — |
| MMLU-Pro | — | 90.3% |
| Vectara Hallucination Rate | — | 13.6% |
| GPQA (HELM) | — | 80.3% |
Multimodal Gemini 3 Pro leads
Claude Fable 5: 45.6 (#14), Gemini 3 Pro: 56.9 (#1)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Vision | 1326 | 1305 |
| LMArena Document | 1496 | 1434 |
| GeoBench | — | 84% |
| VPCT | — | 91% |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
Multilingual Too close to call
Claude Fable 5: 57.6 (#8), Gemini 3 Pro: 57.1 (#14)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1483 | 1474 |
| LMArena Chinese | 1546 | 1522 |
| LMArena French | 1509 | 1492 |
| LMArena German | 1486 | 1517 |
| LMArena Japanese | 1507 | 1513 |
| LMArena Korean | 1493 | 1449 |
| LMArena Russian | 1507 | 1493 |
| LMArena Spanish | 1503 | 1468 |
Instruction Following Claude Fable 5 leads
Claude Fable 5: 78.8 (#7), Gemini 3 Pro: 76.4 (#42)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Instruction Following | 1503 | 1458 |
| IFEval | — | 87.7% |
Long Context Claude Fable 5 leads
Claude Fable 5: 46.3 (#22), Gemini 3 Pro: 44.0 (#75)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1510 | 1472 |
| CL-bench | — | 15.8% |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 76.1 (#5), Gemini 3 Pro: 66.6 (#34)
| Benchmark | Claude Fable 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1491 | 1479 |
| LMArena Creative Writing | 1494 | 1482 |
| EQ-Bench Creative Writing | 1943 | 1525 |
| LMArena Multi-Turn | 1505 | 1484 |
| WildBench | — | 85.9% |
| EQ-Bench 4 | 1340 | — |
Frequently asked questions
Is Claude Fable 5 better than Gemini 3 Pro?
Claude Fable 5 is the stronger model overall, scoring 66.3 to 54.7 on the Noometry Index.
Is Claude Fable 5 or Gemini 3 Pro better for coding?
Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 52.1 in the Noometry coding category.
How many benchmarks do Claude Fable 5 and Gemini 3 Pro share?
39 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Gemini 3 Pro has 67.