Model comparison
Claude Fable 5.1 vs Grok-3 mini
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 41.2 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Claude Fable 5.1 scores higher in 8 categories and Grok-3 mini in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 0.4% for Grok-3 mini.
Side by side
| Claude Fable 5.1 | Grok-3 mini | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 69.0 | 41.2 |
| Released | 2026-09-01 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 52 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), Grok-3 mini: 40.8 (#131)
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| WeirdML | 92.9% | 42.6% |
| LMArena Coding | 1528 | 1379 |
| FrontierCode | 50.9% | — |
| Aider Polyglot | — | 49.3% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| GSO | 88.2% | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |
Agentic & Tool Use Not comparable
Claude Fable 5.1: 50.7 (#5), Grok-3 mini: —
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), Grok-3 mini: 13.6 (#334)
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 90% | 0.4% |
| ARC-AGI-1 | 97.5% | 16.5% |
| LMArena Hard Prompts | 1526 | 1375 |
| Epoch Capabilities Index | 164.7 | 140.35 |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 90% | — |
| CritPt | 31.1% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), Grok-3 mini: 42.1 (#85)
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 77.8% |
| LMArena Math | 1525 | 1386 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), Grok-3 mini: 46.4 (#81)
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1535 | 1395 |
| GPQA Diamond | — | 76.3% |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
Claude Fable 5.1: 53.9 (#4), Grok-3 mini: —
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1318 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), Grok-3 mini: 48.1 (#145)
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1507 | 1352 |
| LMArena Chinese | 1586 | 1387 |
| LMArena French | 1525 | 1357 |
| LMArena German | 1500 | 1349 |
| LMArena Japanese | 1543 | 1342 |
| LMArena Korean | 1534 | 1335 |
| LMArena Russian | 1521 | 1353 |
| LMArena Spanish | 1516 | 1381 |
Instruction Following Too close to call
Claude Fable 5.1: 79.2 (#6), Grok-3 mini: 78.5 (#9)
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1517 | 1357 |
| IFEval | — | 95.1% |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), Grok-3 mini: 41.0 (#147)
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1522 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), Grok-3 mini: 52.5 (#169)
| Benchmark | Claude Fable 5.1 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1510 | 1370 |
| LMArena Creative Writing | 1507 | 1342 |
| LMArena Multi-Turn | 1492 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 2162 | — |
| WildBench | — | 65.1% |
Frequently asked questions
Is Claude Fable 5.1 better than Grok-3 mini?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 41.2 on the Noometry Index.
Is Claude Fable 5.1 or Grok-3 mini better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 40.8 in the Noometry coding category.
How many benchmarks do Claude Fable 5.1 and Grok-3 mini share?
22 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Grok-3 mini has 35.