Model comparison
Claude 3 Haiku vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 25.9 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude 3 Haiku 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 9.8.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 90.9% for Grok-3 mini.
Side by side
| Claude 3 Haiku | Grok-3 mini | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 25.9 | 41.2 |
| Released | 2024-03-07 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Claude 3 Haiku: 26.4 (#325), Grok-3 mini: 40.8 (#131)
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| WeirdML | 9.8% | 42.6% |
| LMArena Coding | 1199 | 1379 |
| Aider Polyglot | — | 49.3% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Claude 3 Haiku leads
Claude 3 Haiku: 16.3 (#307), Grok-3 mini: 13.6 (#334)
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 61.3% |
| LMArena Hard Prompts | 1174 | 1375 |
| Epoch Capabilities Index | 118.35 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| ARC-AGI-1 | — | 16.5% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Grok-3 mini leads
Claude 3 Haiku: 9.8 (#319), Grok-3 mini: 42.1 (#85)
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 77.8% |
| LMArena Math | 1188 | 1386 |
| MATH Level 5 | 14.9% | 90.9% |
| Omni-MATH | — | 31.8% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Claude 3 Haiku: 17.3 (#285), Grok-3 mini: 46.4 (#81)
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 36.3% | 76.3% |
| Confabulations | 34.2% | 10.8% |
| LMArena Expert | 1148 | 1395 |
| MMLU-Pro | — | 79.9% |
| GPQA (HELM) | — | 67.5% |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Grok-3 mini: —
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Grok-3 mini leads
Claude 3 Haiku: 36.0 (#243), Grok-3 mini: 48.1 (#145)
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1178 | 1352 |
| LMArena Chinese | 1155 | 1387 |
| LMArena French | 1195 | 1357 |
| LMArena German | 1174 | 1349 |
| LMArena Japanese | 1102 | 1342 |
| LMArena Korean | 1109 | 1335 |
| LMArena Russian | 1204 | 1353 |
| LMArena Spanish | 1166 | 1381 |
Instruction Following Grok-3 mini leads
Claude 3 Haiku: 61.3 (#247), Grok-3 mini: 78.5 (#9)
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1173 | 1357 |
| IFEval | — | 95.1% |
Long Context Grok-3 mini leads
Claude 3 Haiku: 36.1 (#237), Grok-3 mini: 41.0 (#147)
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1190 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Grok-3 mini leads
Claude 3 Haiku: 29.7 (#291), Grok-3 mini: 52.5 (#169)
| Benchmark | Claude 3 Haiku | Grok-3 mini |
|---|---|---|
| LMArena Text | 1195 | 1370 |
| LMArena Creative Writing | 1157 | 1342 |
| LMArena Multi-Turn | 1190 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 717 | — |
| WildBench | — | 65.1% |
Frequently asked questions
Is Claude 3 Haiku better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Grok-3 mini share?
24 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Grok-3 mini has 35.