Model comparison
Kimi K2 (Jul 2025) vs Qwen2.5 32B Instruct
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 30.1 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Kimi K2 (Jul 2025) scores higher in 4 categories and Qwen2.5 32B Instruct in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 42.7 to 16.2.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 131K.
Side by side
| Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 30.1 |
| Released | 2025-07-12 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $0.57 | $0.70 |
| Output $ / M tokens | $2.30 | $2.80 |
| Results tracked | 42 | 7 |
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), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1399 | — |
| BigCodeBench Complete | — | 52.3% |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Qwen2.5 32B Instruct: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 23.3 (#179), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| Epoch Capabilities Index | 146.01 | 128.52 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1384 | — |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| Omni-MATH | 65.4% | — |
| LMArena Math | 1397 | — |
| MATH Level 5 | — | 56.1% |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 37.3 (#157), Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
| LMArena Expert | 1365 | — |
Multilingual Not comparable
Kimi K2 (Jul 2025): 49.6 (#130), Qwen2.5 32B Instruct: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1372 | — |
| LMArena Chinese | 1415 | — |
| LMArena French | 1379 | — |
| LMArena German | 1387 | — |
| LMArena Japanese | 1349 | — |
| LMArena Korean | 1325 | — |
| LMArena Russian | 1385 | — |
| LMArena Spanish | 1386 | — |
Instruction Following Not comparable
Kimi K2 (Jul 2025): 71.1 (#156), Qwen2.5 32B Instruct: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| IFEval | 85% | — |
| LMArena Instruction Following | 1348 | — |
Long Context Not comparable
Kimi K2 (Jul 2025): 41.2 (#145), Qwen2.5 32B Instruct: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
| LMArena Longer Query | 1353 | — |
Writing & Preference Not comparable
Kimi K2 (Jul 2025): 62.3 (#78), Qwen2.5 32B Instruct: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1380 | — |
| LMArena Creative Writing | 1350 | — |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
| LMArena Multi-Turn | 1371 | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Qwen2.5 32B Instruct?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 30.1 on the Noometry Index.
Which is cheaper, Kimi K2 (Jul 2025) or Qwen2.5 32B Instruct?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.
Is Kimi K2 (Jul 2025) or Qwen2.5 32B Instruct better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 38.7 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 131K.
How many benchmarks do Kimi K2 (Jul 2025) and Qwen2.5 32B Instruct share?
1 benchmark has published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Qwen2.5 32B Instruct has 7.