Model comparison
Claude 3 Haiku vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 25.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 3 categories and Qwen1.5-14B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-14B leads 32.4 to 9.8.
- Qwen1.5-14B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Qwen1.5-14B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.9 | 32.7 |
| Released | 2024-03-07 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Claude 3 Haiku: 26.4 (#325), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1199 | 1138 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Qwen1.5-14B leads
Claude 3 Haiku: 16.3 (#307), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1113 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Qwen1.5-14B leads
Claude 3 Haiku: 9.8 (#319), Qwen1.5-14B: 32.4 (#215)
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1188 | 1125 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Qwen1.5-14B leads
Claude 3 Haiku: 17.3 (#285), Qwen1.5-14B: 29.8 (#232)
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1148 | 1094 |
| MMLU | 73.8% | 68.6% |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Qwen1.5-14B: —
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.0 (#243), Qwen1.5-14B: 30.7 (#262)
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1178 | 1095 |
| LMArena Chinese | 1155 | 1147 |
| LMArena French | 1195 | 1116 |
| LMArena German | 1174 | 1043 |
| LMArena Japanese | 1102 | 1019 |
| LMArena Russian | 1204 | 1046 |
| LMArena Spanish | 1166 | 1085 |
| LMArena Korean | 1109 | — |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.3 (#247), Qwen1.5-14B: 56.8 (#271)
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1173 | 1102 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#237), Qwen1.5-14B: 33.7 (#257)
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1190 | 1113 |
Writing & Preference Qwen1.5-14B leads
Claude 3 Haiku: 29.7 (#291), Qwen1.5-14B: 33.6 (#276)
| Benchmark | Claude 3 Haiku | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1195 | 1128 |
| LMArena Creative Writing | 1157 | 1091 |
| LMArena Multi-Turn | 1190 | 1110 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Qwen1.5-14B share?
17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen1.5-14B has 17.