Model comparison
Claude Sonnet 5 vs Grok-3 mini
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 41.2 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Claude Sonnet 5 scores higher in 7 categories and Grok-3 mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 13.6.
- The biggest single-benchmark swing is WeirdML: 68.8% for Claude Sonnet 5 and 42.6% for Grok-3 mini.
Side by side
| Claude Sonnet 5 | Grok-3 mini | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 54.6 | 41.2 |
| Released | 2026-06-29 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 51 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), Grok-3 mini: 40.8 (#131)
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| WeirdML | 68.8% | 42.6% |
| LMArena Coding | 1483 | 1379 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| Aider Polyglot | — | 49.3% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.8 (#18), Grok-3 mini: —
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), Grok-3 mini: 13.6 (#334)
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1375 |
| Epoch Capabilities Index | 156.21 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 16.5% |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), Grok-3 mini: 42.1 (#85)
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 77.8% |
| LMArena Math | 1467 | 1386 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), Grok-3 mini: 46.4 (#81)
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 90.5% | 76.3% |
| LMArena Expert | 1490 | 1395 |
| SimpleQA Verified | 33.7% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), Grok-3 mini: —
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), Grok-3 mini: 48.1 (#145)
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1431 | 1352 |
| LMArena Chinese | 1477 | 1387 |
| LMArena French | 1460 | 1357 |
| LMArena German | 1440 | 1349 |
| LMArena Japanese | 1422 | 1342 |
| LMArena Korean | 1411 | 1335 |
| LMArena Russian | 1451 | 1353 |
| LMArena Spanish | 1437 | 1381 |
Instruction Following Grok-3 mini leads
Claude Sonnet 5: 76.3 (#41), Grok-3 mini: 78.5 (#9)
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1452 | 1357 |
| IFEval | — | 95.1% |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#55), Grok-3 mini: 41.0 (#147)
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1463 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), Grok-3 mini: 52.5 (#169)
| Benchmark | Claude Sonnet 5 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1442 | 1370 |
| LMArena Creative Writing | 1416 | 1342 |
| LMArena Multi-Turn | 1454 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1794 | — |
| WildBench | — | 65.1% |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than Grok-3 mini?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 41.2 on the Noometry Index.
Is Claude Sonnet 5 or Grok-3 mini better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 40.8 in the Noometry coding category.
How many benchmarks do Claude Sonnet 5 and Grok-3 mini share?
21 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Grok-3 mini has 35.