Model comparison
Claude Fable 5 vs Grok 4
Claude Fable 5 is the stronger model overall, scoring 66.8 to 48.1 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. Claude Fable 5 scores higher in 8 categories and Grok 4 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 36.7.
- The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Claude Fable 5 and 16% for Grok 4.
Side by side
| Claude Fable 5 | Grok 4 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 66.8 | 48.1 |
| Released | 2026-06-07 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 62 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 70.6 (#4), Grok 4: 50.3 (#46)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| WeirdML | 91.9% | 45.7% |
| LMArena Coding | 1519 | 1408 |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| Aider Polyglot | — | 79.6% |
| LMArena WebDev | 1625 | — |
| FrontierSWE | 47% | — |
| SciCode | 61% | — |
| GSO | 78.4% | — |
| MirrorCode | 63.9% | — |
| ALE-Bench | 2,041 | — |
Agentic & Tool Use Claude Fable 5 leads
Claude Fable 5: 54.0 (#2), Grok 4: 32.3 (#68)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| LMArena Search | 1230 | 1142 |
| Terminal-Bench | — | 27.2% |
| APEX-Agents | 63.6% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| PostTrainBench | 41.8% | — |
| BALROG | — | 43.6% |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| METR Time Horizons | — | 66.6% |
| Vending-Bench 2 | 5,680 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#6), Grok 4: 36.7 (#65)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 89.2% | 16% |
| SimpleBench | 81.9% | 60.5% |
| Kagi LLM Benchmark | 91.4% | 73.6% |
| ARC-AGI-1 | 98.5% | 66.7% |
| Chess Puzzles | 41% | 28% |
| LMArena Hard Prompts | 1508 | 1409 |
| Epoch Capabilities Index | 162.06 | 146.44 |
| NYT Connections (extended) | 92.7% | — |
| CritPt | 28.6% | — |
| 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 | — |
| ForecastBench | — | 60.9 |
Math Claude Fable 5 leads
Claude Fable 5: 88.5 (#5), Grok 4: 48.4 (#64)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 84% |
| LMArena Math | 1519 | 1422 |
| FrontierMath (Tiers 1-3) | 87% | — |
| FrontierMath Tier 4 | 90.2% | — |
| ProofBench | 95% | — |
| Omni-MATH | — | 60.3% |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Claude Fable 5 leads
Claude Fable 5: 62.2 (#25), Grok 4: 53.8 (#55)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| GPQA Diamond | 85.9% | 87% |
| LMArena Expert | 1534 | 1415 |
| SimpleQA Verified | 70.7% | — |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
Multimodal Claude Fable 5 leads
Claude Fable 5: 45.3 (#17), Grok 4: 33.7 (#94)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| LMArena Vision | 1324 | 1210 |
| GeoBench | — | 45% |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |
Multilingual Claude Fable 5 leads
Claude Fable 5: 57.3 (#9), Grok 4: 51.8 (#103)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| LMArena Non-English | 1481 | 1403 |
| LMArena Chinese | 1543 | 1427 |
| LMArena French | 1505 | 1418 |
| LMArena German | 1486 | 1429 |
| LMArena Japanese | 1506 | 1394 |
| LMArena Korean | 1488 | 1377 |
| LMArena Russian | 1504 | 1410 |
| LMArena Spanish | 1498 | 1420 |
Instruction Following Too close to call
Claude Fable 5: 78.6 (#8), Grok 4: 79.2 (#5)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1502 | 1387 |
| IFEval | — | 94.9% |
Long Context Grok 4 leads
Claude Fable 5: 46.3 (#23), Grok 4: 63.1 (#4)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1509 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 75.9 (#5), Grok 4: 58.5 (#116)
| Benchmark | Claude Fable 5 | Grok 4 |
|---|---|---|
| LMArena Text | 1491 | 1411 |
| LMArena Creative Writing | 1494 | 1397 |
| LMArena Multi-Turn | 1504 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| EQ-Bench Creative Writing | 1943 | — |
| WildBench | — | 79.7% |
| EQ-Bench 4 | 1340 | — |
Frequently asked questions
Is Claude Fable 5 better than Grok 4?
Claude Fable 5 is the stronger model overall, scoring 66.8 to 48.1 on the Noometry Index.
Is Claude Fable 5 or Grok 4 better for coding?
Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 50.3 in the Noometry coding category.
How many benchmarks do Claude Fable 5 and Grok 4 share?
28 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Grok 4 has 48.