Model comparison
Claude 3 Haiku vs Grok-2 (Dec 2024)
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 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 0 categories and Grok-2 (Dec 2024) in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok-2 (Dec 2024) leads 48.6 to 29.7.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 63.5% for Grok-2 (Dec 2024).
Side by side
| Claude 3 Haiku | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 25.9 | 33.7 |
| Released | 2024-03-07 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-2 (Dec 2024) leads
Claude 3 Haiku: 26.4 (#325), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 9.8% | 22.2% |
| LMArena Coding | 1199 | 1287 |
| BigCodeBench Instruct | 39.4% | — |
| LiveBench Coding | — | 46.4% |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Too close to call
Claude 3 Haiku: 16.3 (#307), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1272 |
| DTBench | 50.1% | 65.2% |
| Epoch Capabilities Index | 118.35 | 130.48 |
| SimpleBench | — | 22.7% |
| Kagi LLM Benchmark | 34.2% | — |
| LiveBench Reasoning | — | 54.8% |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 8.8% | — |
| ForecastBench | 53.2 | — |
| LiveBench | — | 54.3% |
| WinoGrande | 74.2% | — |
Math Grok-2 (Dec 2024) leads
Claude 3 Haiku: 9.8 (#319), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 11.5% |
| LMArena Math | 1188 | 1283 |
| MATH Level 5 | 14.9% | 63.5% |
| LiveBench Math | — | 54.9% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Grok-2 (Dec 2024) leads
Claude 3 Haiku: 17.3 (#285), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 36.3% | 53.8% |
| Confabulations | 34.2% | 20.1% |
| LMArena Expert | 1148 | 1254 |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Grok-2 (Dec 2024): —
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Grok-2 (Dec 2024) leads
Claude 3 Haiku: 36.0 (#243), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1178 | 1282 |
| LMArena Chinese | 1155 | 1289 |
| LMArena French | 1195 | 1318 |
| LMArena German | 1174 | 1287 |
| LMArena Japanese | 1102 | 1244 |
| LMArena Korean | 1109 | 1237 |
| LMArena Russian | 1204 | 1286 |
| LMArena Spanish | 1166 | 1281 |
Instruction Following Grok-2 (Dec 2024) leads
Claude 3 Haiku: 61.3 (#247), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1173 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context Grok-2 (Dec 2024) leads
Claude 3 Haiku: 36.1 (#237), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1190 | 1276 |
Writing & Preference Grok-2 (Dec 2024) leads
Claude 3 Haiku: 29.7 (#291), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | Claude 3 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1195 | 1305 |
| LMArena Creative Writing | 1157 | 1284 |
| LMArena Multi-Turn | 1190 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 717 | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is Claude 3 Haiku better than Grok-2 (Dec 2024)?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Grok-2 (Dec 2024) better for coding?
Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Grok-2 (Dec 2024) share?
24 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Grok-2 (Dec 2024) has 34.