Model comparison
Claude 3.5 Sonnet vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 34.6 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 2 categories and Grok-3 mini in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 42.1 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 77.8% for Grok-3 mini.
Side by side
| Claude 3.5 Sonnet | Grok-3 mini | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 34.6 | 41.2 |
| Released | 2024-06-20 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Claude 3.5 Sonnet: 39.0 (#165), Grok-3 mini: 40.8 (#131)
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| Aider Polyglot | 51.6% | 49.3% |
| WeirdML | 40% | 42.6% |
| LMArena Coding | 1342 | 1379 |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.3 (#67), Grok-3 mini: —
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), Grok-3 mini: 13.6 (#334)
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1375 |
| Epoch Capabilities Index | 133.55 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Grok-3 mini leads
Claude 3.5 Sonnet: 19.2 (#288), Grok-3 mini: 42.1 (#85)
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 77.8% |
| Omni-MATH | 27.6% | 31.8% |
| LMArena Math | 1307 | 1386 |
| MATH Level 5 | 56.9% | 90.9% |
| FrontierMath (Feb 2025 set) | 2.1% | 5.9% |
| LiveBench Math | 52.3% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok-3 mini leads
Claude 3.5 Sonnet: 28.6 (#245), Grok-3 mini: 46.4 (#81)
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 55.3% | 76.3% |
| MMLU-Pro | 77.7% | 79.9% |
| Confabulations | 19.9% | 10.8% |
| GPQA (HELM) | 56.5% | 67.5% |
| LMArena Expert | 1265 | 1395 |
| Humanity's Last Exam | 4.1% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), Grok-3 mini: —
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Grok-3 mini leads
Claude 3.5 Sonnet: 43.2 (#185), Grok-3 mini: 48.1 (#145)
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1283 | 1352 |
| LMArena Chinese | 1272 | 1387 |
| LMArena French | 1305 | 1357 |
| LMArena German | 1297 | 1349 |
| LMArena Japanese | 1234 | 1342 |
| LMArena Korean | 1200 | 1335 |
| LMArena Russian | 1306 | 1353 |
| LMArena Spanish | 1290 | 1381 |
Instruction Following Grok-3 mini leads
Claude 3.5 Sonnet: 68.8 (#182), Grok-3 mini: 78.5 (#9)
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| IFEval | 85.5% | 95.1% |
| LMArena Instruction Following | 1297 | 1357 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Grok-3 mini leads
Claude 3.5 Sonnet: 39.9 (#167), Grok-3 mini: 41.0 (#147)
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1311 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Too close to call
Claude 3.5 Sonnet: 52.9 (#164), Grok-3 mini: 52.5 (#169)
| Benchmark | Claude 3.5 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Text | 1298 | 1370 |
| LMArena Creative Writing | 1292 | 1342 |
| Short-Story Creative Writing | 80.3% | 73.5% |
| WildBench | 79.2% | 65.1% |
| LMArena Multi-Turn | 1326 | 1355 |
| EQ-Bench Creative Writing | 1451 | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Grok-3 mini share?
31 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Grok-3 mini has 35.