Model comparison
Claude 3 Haiku vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 25.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Qwen1.5-32B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 33.0 to 9.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 50.1% for Claude 3 Haiku and 42% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Qwen1.5-32B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.9 | 30.5 |
| Released | 2024-03-07 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Claude 3 Haiku: 26.4 (#325), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 39.4% | 32.3% |
| LMArena Coding | 1199 | 1155 |
| BigCodeBench Complete | 50.1% | 42% |
| WeirdML | 9.8% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Qwen1.5-32B leads
Claude 3 Haiku: 16.3 (#307), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1130 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Qwen1.5-32B leads
Claude 3 Haiku: 9.8 (#319), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1188 | 1155 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Claude 3 Haiku leads
Claude 3 Haiku: 17.3 (#285), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 36.3% | 30.7% |
| LMArena Expert | 1148 | 1126 |
| MMLU | 73.8% | 74.4% |
| Confabulations | 34.2% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Qwen1.5-32B: —
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.0 (#243), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1178 | 1106 |
| LMArena Chinese | 1155 | 1177 |
| LMArena French | 1195 | 1101 |
| LMArena German | 1174 | 1058 |
| LMArena Japanese | 1102 | 1027 |
| LMArena Korean | 1109 | 1008 |
| LMArena Russian | 1204 | 1073 |
| LMArena Spanish | 1166 | 1089 |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.3 (#247), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1173 | 1116 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#237), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1190 | 1146 |
Writing & Preference Qwen1.5-32B leads
Claude 3 Haiku: 29.7 (#291), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Claude 3 Haiku | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1195 | 1137 |
| LMArena Creative Writing | 1157 | 1083 |
| LMArena Multi-Turn | 1190 | 1140 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.7 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Qwen1.5-32B share?
21 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen1.5-32B has 21.