Model comparison
Claude 3 Haiku vs Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 25.7 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 Qwen3-Coder 480B-A35B Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Coder 480B-A35B Instruct leads 34.9 to 9.2.
- The biggest single-benchmark swing is WeirdML: 9.8% for Claude 3 Haiku and 41.2% for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.7 | 37.7 |
| Released | 2024-03-07 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 37 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
Claude 3 Haiku: 26.1 (#320), Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 9.8% | 41.2% |
| LMArena Coding | 1199 | 1413 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Claude 3 Haiku: 15.7 (#303), Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 49.5% |
| LMArena Hard Prompts | 1174 | 1372 |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Qwen3-Coder 480B-A35B Instruct leads
Claude 3 Haiku: 9.2 (#313), Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1188 | 1364 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Qwen3-Coder 480B-A35B Instruct leads
Claude 3 Haiku: 17.3 (#280), Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1148 | 1337 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.1 (#123), Qwen3-Coder 480B-A35B Instruct: —
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
Claude 3 Haiku: 36.1 (#238), Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1178 | 1345 |
| LMArena Chinese | 1155 | 1356 |
| LMArena French | 1194 | 1394 |
| LMArena German | 1174 | 1324 |
| LMArena Japanese | 1102 | 1309 |
| LMArena Korean | 1108 | 1307 |
| LMArena Russian | 1204 | 1367 |
| LMArena Spanish | 1165 | 1360 |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
Claude 3 Haiku: 61.5 (#242), Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1174 | 1356 |
Long Context Qwen3-Coder 480B-A35B Instruct leads
Claude 3 Haiku: 36.1 (#232), Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1191 | 1379 |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
Claude 3 Haiku: 29.8 (#286), Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)
| Benchmark | Claude 3 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1195 | 1356 |
| LMArena Creative Writing | 1157 | 1333 |
| LMArena Multi-Turn | 1190 | 1365 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 36.2 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Qwen3-Coder 480B-A35B Instruct share?
19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.