Model comparison
Claude 3 Sonnet vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 29.0 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 42.1 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 77.8% for Grok-3 mini.
Side by side
| Claude 3 Sonnet | Grok-3 mini | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 29.0 | 41.2 |
| Released | 2024-02-29 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Claude 3 Sonnet: 29.6 (#302), Grok-3 mini: 40.8 (#131)
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| WeirdML | 10.2% | 42.6% |
| LMArena Coding | 1223 | 1379 |
| Aider Polyglot | — | 49.3% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 20.5 (#237), Grok-3 mini: 13.6 (#334)
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1375 |
| Epoch Capabilities Index | 120.7 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| DTBench | 53.6% | — |
| WinoGrande | 75.1% | — |
Math Grok-3 mini leads
Claude 3 Sonnet: 10.7 (#310), Grok-3 mini: 42.1 (#85)
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 77.8% |
| LMArena Math | 1213 | 1386 |
| MATH Level 5 | 18.2% | 90.9% |
| Omni-MATH | — | 31.8% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Claude 3 Sonnet: 21.1 (#276), Grok-3 mini: 46.4 (#81)
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 40.6% | 76.3% |
| LMArena Expert | 1173 | 1395 |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Grok-3 mini: —
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Grok-3 mini leads
Claude 3 Sonnet: 37.8 (#234), Grok-3 mini: 48.1 (#145)
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1205 | 1352 |
| LMArena Chinese | 1189 | 1387 |
| LMArena French | 1229 | 1357 |
| LMArena German | 1204 | 1349 |
| LMArena Japanese | 1131 | 1342 |
| LMArena Korean | 1128 | 1335 |
| LMArena Russian | 1227 | 1353 |
| LMArena Spanish | 1204 | 1381 |
Instruction Following Grok-3 mini leads
Claude 3 Sonnet: 62.8 (#235), Grok-3 mini: 78.5 (#9)
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1199 | 1357 |
| IFEval | — | 95.1% |
Long Context Grok-3 mini leads
Claude 3 Sonnet: 36.7 (#228), Grok-3 mini: 41.0 (#147)
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1211 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Grok-3 mini leads
Claude 3 Sonnet: 42.1 (#238), Grok-3 mini: 52.5 (#169)
| Benchmark | Claude 3 Sonnet | Grok-3 mini |
|---|---|---|
| LMArena Text | 1218 | 1370 |
| LMArena Creative Writing | 1186 | 1342 |
| LMArena Multi-Turn | 1227 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
Frequently asked questions
Is Claude 3 Sonnet better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Grok-3 mini share?
22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Grok-3 mini has 35.