Model comparison
Claude 3 Haiku vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 25.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Max leads 47.8 to 29.7.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 67.2% for Qwen Max.
Side by side
| Claude 3 Haiku | Qwen Max | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.9 | 34.7 |
| Released | 2024-03-07 | 2024-04-03 |
| Weights | Proprietary | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 37 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Max leads
Claude 3 Haiku: 26.4 (#325), Qwen Max: 30.7 (#292)
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| LMArena Coding | 1199 | 1288 |
| Aider Polyglot | — | 21.8% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Qwen Max leads
Claude 3 Haiku: 16.3 (#307), Qwen Max: 25.1 (#151)
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1269 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Qwen Max leads
Claude 3 Haiku: 9.8 (#319), Qwen Max: 22.3 (#276)
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 16.1% |
| LMArena Math | 1188 | 1275 |
| MATH Level 5 | 14.9% | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Qwen Max leads
Claude 3 Haiku: 17.3 (#285), Qwen Max: 30.3 (#228)
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| GPQA Diamond | 36.3% | 56.1% |
| LMArena Expert | 1148 | 1248 |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Qwen Max: —
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Qwen Max leads
Claude 3 Haiku: 36.0 (#243), Qwen Max: 41.8 (#202)
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| LMArena Non-English | 1178 | 1263 |
| LMArena Chinese | 1155 | 1254 |
| LMArena French | 1195 | 1330 |
| LMArena German | 1174 | 1254 |
| LMArena Japanese | 1102 | 1205 |
| LMArena Korean | 1109 | 1142 |
| LMArena Russian | 1204 | 1274 |
| LMArena Spanish | 1166 | 1290 |
Instruction Following Qwen Max leads
Claude 3 Haiku: 61.3 (#247), Qwen Max: 66.5 (#208)
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1173 | 1262 |
Long Context Qwen Max leads
Claude 3 Haiku: 36.1 (#237), Qwen Max: 39.4 (#180)
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1190 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Claude 3 Haiku: 29.7 (#291), Qwen Max: 47.8 (#205)
| Benchmark | Claude 3 Haiku | Qwen Max |
|---|---|---|
| LMArena Text | 1195 | 1282 |
| LMArena Creative Writing | 1157 | 1248 |
| LMArena Multi-Turn | 1190 | 1277 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Qwen Max better for coding?
Qwen Max scores higher on coding benchmarks: 30.7 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Qwen Max share?
20 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen Max has 23.