Model comparison
Claude 3.7 Sonnet vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 39.5 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 3 categories and Grok-3 mini in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.3 to 41.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 77.8% for Grok-3 mini.
Side by side
| Claude 3.7 Sonnet | Grok-3 mini | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 39.5 | 41.2 |
| Released | 2025-02-24 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 58 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.7 Sonnet: 40.6 (#136), Grok-3 mini: 40.8 (#131)
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| Aider Polyglot | 64.9% | 49.3% |
| LMArena Coding | 1361 | 1379 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| GSO | 3.8% | — |
| WeirdML | — | 42.6% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
Claude 3.7 Sonnet: 34.1 (#50), Grok-3 mini: —
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 18.6 (#277), Grok-3 mini: 13.6 (#334)
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 0.9% | 0.4% |
| ARC-AGI-1 | 28.6% | 16.5% |
| LMArena Hard Prompts | 1333 | 1375 |
| Epoch Capabilities Index | 141.16 | 140.35 |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 61.3% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| LiveBench Data Analysis | 74% | — |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Grok-3 mini leads
Claude 3.7 Sonnet: 37.5 (#153), Grok-3 mini: 42.1 (#85)
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 77.8% |
| Omni-MATH | 33% | 31.8% |
| LMArena Math | 1337 | 1386 |
| MATH Level 5 | 91.2% | 90.9% |
| FrontierMath (Feb 2025 set) | 4.1% | 5.9% |
| LiveBench Math | 79% | — |
Knowledge Grok-3 mini leads
Claude 3.7 Sonnet: 39.8 (#130), Grok-3 mini: 46.4 (#81)
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 79.7% | 76.3% |
| MMLU-Pro | 78.4% | 79.9% |
| Confabulations | 14.7% | 10.8% |
| GPQA (HELM) | 60.8% | 67.5% |
| LMArena Expert | 1321 | 1395 |
| Humanity's Last Exam | 8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), Grok-3 mini: —
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Grok-3 mini leads
Claude 3.7 Sonnet: 44.1 (#179), Grok-3 mini: 48.1 (#145)
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1296 | 1352 |
| LMArena Chinese | 1299 | 1387 |
| LMArena French | 1303 | 1357 |
| LMArena German | 1301 | 1349 |
| LMArena Japanese | 1267 | 1342 |
| LMArena Korean | 1249 | 1335 |
| LMArena Russian | 1311 | 1353 |
| LMArena Spanish | 1298 | 1381 |
Instruction Following Grok-3 mini leads
Claude 3.7 Sonnet: 72.9 (#125), Grok-3 mini: 78.5 (#9)
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| IFEval | 83.4% | 95.1% |
| LMArena Instruction Following | 1352 | 1357 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Grok-3 mini: 41.0 (#147)
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | 83.3% | 66.7% |
| LMArena Longer Query | 1373 | 1372 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.4 (#150), Grok-3 mini: 52.5 (#169)
| Benchmark | Claude 3.7 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Text | 1314 | 1370 |
| LMArena Creative Writing | 1332 | 1342 |
| Short-Story Creative Writing | 81.1% | 73.5% |
| WildBench | 81.4% | 65.1% |
| LMArena Multi-Turn | 1339 | 1355 |
| EQ-Bench Creative Writing | 1412 | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Grok-3 mini better for coding?
They score almost the same on coding (40.6 vs 40.8); test both on your own repository before choosing.
How many benchmarks do Claude 3.7 Sonnet and Grok-3 mini share?
33 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Grok-3 mini has 35.