Model comparison
Kimi K2 (Jul 2025) vs Qwen3-Coder 480B-A35B Instruct
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 38.1 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 6 categories and Qwen3-Coder 480B-A35B Instruct in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Kimi K2 (Jul 2025) leads 32.4 to 23.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 64.4% for Kimi K2 (Jul 2025) and 49.5% for Qwen3-Coder 480B-A35B Instruct.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
Side by side
| Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 38.1 |
| Released | 2025-07-12 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 66K |
| Input $ / M tokens | $0.57 | $1.50 |
| Output $ / M tokens | $2.30 | $7.50 |
| Results tracked | 42 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.4 (#102), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 63.4% | 55.4% |
| GSO | 4.9% | 4.9% |
| WeirdML | 42.8% | 41.2% |
| LMArena Coding | 1399 | 1412 |
| ALE-Bench | 597.5 | 461.45 |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1275 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 32.4 (#64), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | 35.7% | 27.2% |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Kimi K2 (Jul 2025): 23.3 (#179), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 64.4% | 49.5% |
| LMArena Hard Prompts | 1384 | 1372 |
| SimpleBench | 26.3% | — |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1397 | 1365 |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Too close to call
Kimi K2 (Jul 2025): 37.3 (#157), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1365 | 1338 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multilingual Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 49.6 (#130), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1372 | 1346 |
| LMArena Chinese | 1415 | 1357 |
| LMArena French | 1379 | 1398 |
| LMArena German | 1387 | 1325 |
| LMArena Japanese | 1349 | 1310 |
| LMArena Korean | 1325 | 1305 |
| LMArena Russian | 1385 | 1366 |
| LMArena Spanish | 1386 | 1360 |
Instruction Following Too close to call
Kimi K2 (Jul 2025): 71.1 (#156), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1348 | 1355 |
| IFEval | 85% | — |
Long Context Too close to call
Kimi K2 (Jul 2025): 41.2 (#145), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1353 | 1378 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1380 | 1357 |
| LMArena Creative Writing | 1350 | 1333 |
| LMArena Multi-Turn | 1371 | 1365 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Qwen3-Coder 480B-A35B Instruct?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 38.1 on the Noometry Index.
Which is cheaper, Kimi K2 (Jul 2025) or Qwen3-Coder 480B-A35B Instruct?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Kimi K2 (Jul 2025) or Qwen3-Coder 480B-A35B Instruct better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2 (Jul 2025) and Qwen3-Coder 480B-A35B Instruct share?
23 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.