Model comparison
Claude 3.5 Haiku vs Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 28.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Qwen3-Coder 480B-A35B Instruct in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Coder 480B-A35B Instruct leads 34.9 to 13.7.
- The biggest single-benchmark swing is WeirdML: 30.7% for Claude 3.5 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 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 28.9 | 37.7 |
| Released | 2024-10-22 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 49 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
Claude 3.5 Haiku: 32.6 (#258), Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 30.7% | 41.2% |
| LMArena Coding | 1287 | 1413 |
| SWE-bench Verified (bash only) | — | 55.4% |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1275 |
| SciCode | 27.4% | — |
| GSO | — | 4.9% |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Claude 3.5 Haiku leads
Claude 3.5 Haiku: 27.7 (#90), Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| BALROG | 19.3% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Claude 3.5 Haiku: 17.1 (#286), Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| Epoch Capabilities Index | 127.15 | — |
| LiveBench | 43.5% | — |
Math Qwen3-Coder 480B-A35B Instruct leads
Claude 3.5 Haiku: 13.7 (#294), Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1244 | 1364 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3-Coder 480B-A35B Instruct leads
Claude 3.5 Haiku: 18.7 (#276), Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1208 | 1337 |
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.3 (#113), Qwen3-Coder 480B-A35B Instruct: —
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
Claude 3.5 Haiku: 40.2 (#213), Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1238 | 1345 |
| LMArena Chinese | 1229 | 1356 |
| LMArena French | 1262 | 1394 |
| LMArena German | 1237 | 1324 |
| LMArena Japanese | 1175 | 1309 |
| LMArena Korean | 1172 | 1307 |
| LMArena Russian | 1253 | 1367 |
| LMArena Spanish | 1261 | 1360 |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
Claude 3.5 Haiku: 63.1 (#229), Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1241 | 1356 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Qwen3-Coder 480B-A35B Instruct leads
Claude 3.5 Haiku: 38.3 (#195), Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1261 | 1379 |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
Claude 3.5 Haiku: 42.9 (#228), Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)
| Benchmark | Claude 3.5 Haiku | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1255 | 1356 |
| LMArena Creative Writing | 1233 | 1333 |
| LMArena Multi-Turn | 1265 | 1365 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 28.9 on the Noometry Index.
Is Claude 3.5 Haiku or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 36.2 versus 32.6 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Qwen3-Coder 480B-A35B Instruct share?
18 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.