Model comparison
Kimi K2.5 vs Qwen2.5-Coder-32B
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.4 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Kimi K2.5 leads 48.8 to 22.6.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 70.8% for Kimi K2.5 and 9% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Kimi K2.5 accepts more context: 262K tokens versus 33K.
Side by side
| Kimi K2.5 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 48.1 | 33.4 |
| Released | 2026-01-27 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 262K | 33K |
| Max output | 262K | 29K |
| Input $ / M tokens | $0.45 | $0.66 |
| Output $ / M tokens | $2.25 | $1 |
| Results tracked | 51 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Kimi K2.5: 48.8 (#53), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | 70.8% | 9% |
| LMArena Coding | 1474 | 1276 |
| SWE-bench Verified | 73.8% | — |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 821.65 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
Kimi K2.5: 34.2 (#48), Qwen2.5-Coder-32B: —
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1251 |
| Epoch Capabilities Index | 148.03 | 119.49 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| NYT Connections (extended) | 69.9% | — |
| ARC-AGI-1 | 65.3% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Kimi K2.5 leads
Kimi K2.5: 51.8 (#53), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1470 | 1251 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| LiveBench Math | — | 46.6% |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 93% |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1466 | 1221 |
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Qwen2.5-Coder-32B: —
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Kimi K2.5 leads
Kimi K2.5: 53.9 (#53), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1433 | 1205 |
| LMArena Chinese | 1495 | 1222 |
| LMArena Russian | 1435 | 1228 |
| LMArena French | 1454 | — |
| LMArena German | 1441 | — |
| LMArena Japanese | 1421 | — |
| LMArena Korean | 1410 | — |
| LMArena Spanish | 1450 | — |
Instruction Following Kimi K2.5 leads
Kimi K2.5: 75.3 (#64), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1431 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1445 | 1251 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |
Writing & Preference Kimi K2.5 leads
Kimi K2.5: 65.1 (#53), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Kimi K2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1445 | 1230 |
| LMArena Creative Writing | 1423 | 1174 |
| LMArena Multi-Turn | 1444 | 1222 |
| EQ-Bench Creative Writing | 1579 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Kimi K2.5 better than Qwen2.5-Coder-32B?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.4 on the Noometry Index.
Which is cheaper, Kimi K2.5 or Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is Kimi K2.5 or Qwen2.5-Coder-32B better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 33K.
How many benchmarks do Kimi K2.5 and Qwen2.5-Coder-32B share?
14 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen2.5-Coder-32B has 31.