Model comparison
Claude 3.5 Haiku vs Grok-2 (Dec 2024)
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 29.2 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Grok-2 (Dec 2024) in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-2 (Dec 2024) leads 29.8 to 18.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 28.1% for Claude 3.5 Haiku and 54.8% for Grok-2 (Dec 2024).
Side by side
| Claude 3.5 Haiku | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 29.2 | 33.7 |
| Released | 2024-10-22 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 49 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.5 Haiku: 32.9 (#265), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 30.7% | 22.2% |
| LiveBench Coding | 51.4% | 46.4% |
| LMArena Coding | 1286 | 1287 |
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), Grok-2 (Dec 2024): —
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Too close to call
Claude 3.5 Haiku: 17.7 (#290), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Reasoning | 28.1% | 54.8% |
| LMArena Hard Prompts | 1251 | 1272 |
| DTBench | 56.7% | 65.2% |
| LiveBench Data Analysis | 48.5% | 54.5% |
| Epoch Capabilities Index | 127.15 | 130.48 |
| LiveBench | 43.5% | 54.3% |
| SimpleBench | — | 22.7% |
| CritPt | 0% | — |
Math Grok-2 (Dec 2024) leads
Claude 3.5 Haiku: 14.7 (#300), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 11.5% |
| LiveBench Math | 35.5% | 54.9% |
| LMArena Math | 1244 | 1283 |
| MATH Level 5 | 46.4% | 63.5% |
| FrontierMath (Feb 2025 set) | 0.3% | 0.7% |
| Omni-MATH | 22.4% | — |
Knowledge Grok-2 (Dec 2024) leads
Claude 3.5 Haiku: 18.7 (#281), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 38.1% | 53.8% |
| Confabulations | 36.7% | 20.1% |
| LMArena Expert | 1208 | 1254 |
| MMLU-Pro | 60.5% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), Grok-2 (Dec 2024): —
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Grok-2 (Dec 2024) leads
Claude 3.5 Haiku: 40.0 (#218), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1238 | 1282 |
| LMArena Chinese | 1229 | 1289 |
| LMArena French | 1264 | 1318 |
| LMArena German | 1237 | 1287 |
| LMArena Japanese | 1175 | 1244 |
| LMArena Korean | 1173 | 1237 |
| LMArena Russian | 1253 | 1286 |
| LMArena Spanish | 1261 | 1281 |
Instruction Following Grok-2 (Dec 2024) leads
Claude 3.5 Haiku: 62.9 (#234), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Instruction Following | 61.9% | 69.6% |
| LMArena Instruction Following | 1241 | 1270 |
| IFEval | 79.2% | — |
Long Context Too close to call
Claude 3.5 Haiku: 38.3 (#200), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1261 | 1276 |
Writing & Preference Grok-2 (Dec 2024) leads
Claude 3.5 Haiku: 42.7 (#234), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | Claude 3.5 Haiku | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1255 | 1305 |
| LMArena Creative Writing | 1233 | 1284 |
| Short-Story Creative Writing | 73.5% | 63.6% |
| LMArena Multi-Turn | 1265 | 1290 |
| LiveBench Language | 35.4% | 45.6% |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Grok-2 (Dec 2024)?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Grok-2 (Dec 2024) better for coding?
They score almost the same on coding (32.9 vs 33.3); test both on your own repository before choosing.
How many benchmarks do Claude 3.5 Haiku and Grok-2 (Dec 2024) share?
33 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Grok-2 (Dec 2024) has 34.