Model comparison
Claude Fable 5 vs Grok 3
Claude Fable 5 is the stronger model overall, scoring 66.3 to 39.6 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and Grok 3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 13.8.
- The biggest single-benchmark swing is ARC-AGI-1: 98.5% for Claude Fable 5 and 5.5% for Grok 3.
Side by side
| Claude Fable 5 | Grok 3 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 66.3 | 39.6 |
| Released | 2026-06-07 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 61 | 40 |
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), Grok 3: 41.5 (#113)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| WeirdML | 91.9% | 37.2% |
| LMArena Coding | 1519 | 1432 |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| Aider Polyglot | — | 53.3% |
| LMArena WebDev | 1626 | — |
| FrontierSWE | 47% | — |
| SciCode | 61% | — |
| MirrorCode | 63.9% | — |
| ALE-Bench | 2,041 | — |
Agentic & Tool Use Claude Fable 5 leads
Claude Fable 5: 54.1 (#2), Grok 3: 30.2 (#69)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| APEX-Agents | 63.6% | — |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| BALROG | — | 29.5% |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#4), Grok 3: 13.8 (#322)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| ARC-AGI-2 | 89.2% | 0% |
| SimpleBench | 81.9% | 36.1% |
| Kagi LLM Benchmark | 91.4% | 61.3% |
| ARC-AGI-1 | 98.5% | 5.5% |
| LMArena Hard Prompts | 1508 | 1433 |
| Epoch Capabilities Index | 163.6 | 138.34 |
| NYT Connections (extended) | 92.7% | — |
| CritPt | 28.6% | — |
| Chess Puzzles | 41% | — |
| EnigmaEval | 39.3% | — |
| 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 | — |
Math Claude Fable 5 leads
Claude Fable 5: 88.4 (#5), Grok 3: 36.2 (#122)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 55.6% |
| LMArena Math | 1519 | 1390 |
| FrontierMath (Tiers 1-3) | 87% | — |
| FrontierMath Tier 4 | 90.2% | — |
| ProofBench | 95% | — |
| Omni-MATH | — | 46.4% |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Claude Fable 5 leads
Claude Fable 5: 62.3 (#22), Grok 3: 46.0 (#76)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| GPQA Diamond | 85.9% | 75.8% |
| LMArena Expert | 1534 | 1420 |
| SimpleQA Verified | 70.7% | — |
| MMLU-Pro | — | 78.8% |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 5.8% |
| GPQA (HELM) | — | 65% |
Multimodal Not comparable
Claude Fable 5: 45.6 (#14), Grok 3: —
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| LMArena Vision | 1326 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |
Multilingual Claude Fable 5 leads
Claude Fable 5: 57.6 (#8), Grok 3: 52.5 (#81)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| LMArena Non-English | 1483 | 1411 |
| LMArena Chinese | 1546 | 1448 |
| LMArena French | 1509 | 1460 |
| LMArena German | 1486 | 1431 |
| LMArena Japanese | 1507 | 1389 |
| LMArena Korean | 1493 | 1374 |
| LMArena Russian | 1507 | 1416 |
| LMArena Spanish | 1503 | 1417 |
Instruction Following Claude Fable 5 leads
Claude Fable 5: 78.8 (#7), Grok 3: 75.2 (#69)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| LMArena Instruction Following | 1503 | 1409 |
| IFEval | — | 88.4% |
Long Context Claude Fable 5 leads
Claude Fable 5: 46.3 (#22), Grok 3: 38.7 (#187)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1510 | 1439 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 76.1 (#5), Grok 3: 56.0 (#136)
| Benchmark | Claude Fable 5 | Grok 3 |
|---|---|---|
| LMArena Text | 1491 | 1426 |
| LMArena Creative Writing | 1494 | 1414 |
| EQ-Bench Creative Writing | 1943 | 1186 |
| LMArena Multi-Turn | 1505 | 1424 |
| Short-Story Creative Writing | — | 76.4% |
| WildBench | — | 84.9% |
| EQ-Bench 4 | 1340 | — |
Frequently asked questions
Is Claude Fable 5 better than Grok 3?
Claude Fable 5 is the stronger model overall, scoring 66.3 to 39.6 on the Noometry Index.
Is Claude Fable 5 or Grok 3 better for coding?
Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 41.5 in the Noometry coding category.
How many benchmarks do Claude Fable 5 and Grok 3 share?
26 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Grok 3 has 40.