Model comparison
Kimi K2.5 vs Qwen2-72B
Kimi K2.5 is the stronger model overall, scoring 48.1 to 30.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Kimi K2.5 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 87.6% for Kimi K2.5 and 40.8% for Qwen2-72B.
Side by side
| Kimi K2.5 | Qwen2-72B | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 48.1 | 30.0 |
| Released | 2026-01-27 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 51 | 26 |
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), Qwen2-72B: 29.1 (#310)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| WeirdML | 45.6% | 11.3% |
| LMArena Coding | 1474 | 1196 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 821.65 | — |
Agentic & Tool Use Kimi K2.5 leads
Kimi K2.5: 34.2 (#48), Qwen2-72B: 17.0 (#146)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| TheAgentCompany | — | 1.1% |
| OSWorld | 63.3% | — |
| METR Time Horizons | — | 29.9% |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Qwen2-72B: 23.2 (#181)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1191 |
| Epoch Capabilities Index | 148.03 | 125.28 |
| 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% | — |
Math Kimi K2.5 leads
Kimi K2.5: 51.8 (#53), Qwen2-72B: 30.2 (#236)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1470 | 1235 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| MATH Level 5 | — | 39.1% |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Qwen2-72B: 21.2 (#275)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 87.6% | 40.8% |
| LMArena Expert | 1466 | 1171 |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |
| MMLU | — | 82.4% |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Qwen2-72B: —
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Kimi K2.5 leads
Kimi K2.5: 53.9 (#53), Qwen2-72B: 35.9 (#244)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1433 | 1176 |
| LMArena Chinese | 1495 | 1240 |
| LMArena French | 1454 | 1170 |
| LMArena German | 1441 | 1151 |
| LMArena Japanese | 1421 | 1111 |
| LMArena Korean | 1410 | 1083 |
| LMArena Russian | 1435 | 1169 |
| LMArena Spanish | 1450 | 1169 |
Instruction Following Kimi K2.5 leads
Kimi K2.5: 75.3 (#64), Qwen2-72B: 61.7 (#241)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1431 | 1181 |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Qwen2-72B: 36.1 (#235)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1445 | 1192 |
| 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), Qwen2-72B: 40.8 (#241)
| Benchmark | Kimi K2.5 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1445 | 1203 |
| LMArena Creative Writing | 1423 | 1181 |
| LMArena Multi-Turn | 1444 | 1196 |
| EQ-Bench Creative Writing | 1579 | — |
Frequently asked questions
Is Kimi K2.5 better than Qwen2-72B?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 30.0 on the Noometry Index.
Is Kimi K2.5 or Qwen2-72B better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 29.1 in the Noometry coding category.
How many benchmarks do Kimi K2.5 and Qwen2-72B share?
20 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen2-72B has 26.