Model comparison
Claude 3 Haiku vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 25.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 29.7.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 65.3% for Qwen Plus.
Side by side
| Claude 3 Haiku | Qwen Plus | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.9 | 37.1 |
| Released | 2024-03-07 | 2024-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 37 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Claude 3 Haiku: 26.4 (#325), Qwen Plus: 38.9 (#167)
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| LMArena Coding | 1199 | 1328 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Qwen Plus leads
Claude 3 Haiku: 16.3 (#307), Qwen Plus: 28.4 (#107)
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 63.3% |
| LMArena Hard Prompts | 1174 | 1317 |
| DTBench | 50.1% | 81.1% |
| LMCA | 8.8% | 24% |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Qwen Plus leads
Claude 3 Haiku: 9.8 (#319), Qwen Plus: 23.3 (#271)
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 17.8% |
| LMArena Math | 1188 | 1326 |
| MATH Level 5 | 14.9% | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Qwen Plus leads
Claude 3 Haiku: 17.3 (#285), Qwen Plus: 27.4 (#251)
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| GPQA Diamond | 36.3% | 48.1% |
| LMArena Expert | 1148 | 1328 |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Qwen Plus: —
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Qwen Plus leads
Claude 3 Haiku: 36.0 (#243), Qwen Plus: 45.1 (#175)
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1178 | 1310 |
| LMArena Chinese | 1155 | 1347 |
| LMArena Japanese | 1102 | 1251 |
| LMArena Russian | 1204 | 1323 |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Korean | 1109 | — |
| LMArena Spanish | 1166 | — |
Instruction Following Qwen Plus leads
Claude 3 Haiku: 61.3 (#247), Qwen Plus: 68.8 (#181)
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1173 | 1303 |
Long Context Qwen Plus leads
Claude 3 Haiku: 36.1 (#237), Qwen Plus: 40.3 (#158)
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1190 | 1324 |
Writing & Preference Qwen Plus leads
Claude 3 Haiku: 29.7 (#291), Qwen Plus: 52.2 (#176)
| Benchmark | Claude 3 Haiku | Qwen Plus |
|---|---|---|
| LMArena Text | 1195 | 1326 |
| LMArena Creative Writing | 1157 | 1293 |
| LMArena Multi-Turn | 1190 | 1336 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Qwen Plus share?
19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen Plus has 20.