Model comparison
Mistral Large vs Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 31.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Mistral Large 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 37.6 to 18.2.
- Both cost about the same: $2 input and $6 output per million tokens.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Large | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 38.1 |
| Released | 2024-02-26 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $6 | $7.50 |
| Results tracked | 51 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
Mistral Large: 34.3 (#240), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Coding | 1277 | 1412 |
| ALE-Bench | 264.7 | 461.45 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| SciCode | 36.2% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| AlgoTune | — | 1.44 |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Mistral Large leads
Mistral Large: 28.6 (#89), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Mistral Large: 15.8 (#310), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1372 |
| SimpleBench | 22.5% | — |
| Kagi LLM Benchmark | — | 49.5% |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3-Coder 480B-A35B Instruct leads
Mistral Large: 18.2 (#291), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1262 | 1365 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3-Coder 480B-A35B Instruct leads
Mistral Large: 30.1 (#230), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1232 | 1338 |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
Mistral Large: 40.0 (#219), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1237 | 1346 |
| LMArena Chinese | 1240 | 1357 |
| LMArena French | 1325 | 1398 |
| LMArena German | 1254 | 1325 |
| LMArena Japanese | 1188 | 1310 |
| LMArena Korean | 1202 | 1305 |
| LMArena Russian | 1257 | 1366 |
| LMArena Spanish | 1268 | 1360 |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
Mistral Large: 67.9 (#191), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1249 | 1355 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3-Coder 480B-A35B Instruct leads
Mistral Large: 38.3 (#199), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1261 | 1378 |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
Mistral Large: 40.7 (#242), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Mistral Large | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1266 | 1357 |
| LMArena Creative Writing | 1243 | 1333 |
| LMArena Multi-Turn | 1260 | 1365 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 35.5 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 131K.
How many benchmarks do Mistral Large and Qwen3-Coder 480B-A35B Instruct share?
18 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.