Model comparison
Kimi K2 Thinking Turbo vs Qwen2-72B
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 29.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 84.2% for Kimi K2 Thinking Turbo and 40.8% for Qwen2-72B.
Side by side
| Kimi K2 Thinking Turbo | Qwen2-72B | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 45.4 | 29.5 |
| Released | 2025-11-06 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 38.1 (#166), Qwen2-72B: 28.7 (#303)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1454 | 1196 |
| LMArena WebDev | 1322 | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Kimi K2 Thinking Turbo: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 31.4 (#72), Qwen2-72B: 22.2 (#184)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1191 |
| Chess Puzzles | 20% | — |
| Epoch Capabilities Index | — | 125.27 |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 45.5 (#62), Qwen2-72B: 27.9 (#232)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| LMArena Math | 1429 | 1235 |
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#64), Qwen2-72B: 21.2 (#270)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 84.2% | 40.8% |
| LMArena Expert | 1439 | 1171 |
| MMLU | — | 82.4% |
Multilingual Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 51.6 (#104), Qwen2-72B: 36.0 (#239)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1398 | 1176 |
| LMArena Chinese | 1457 | 1240 |
| LMArena French | 1425 | 1169 |
| LMArena German | 1390 | 1151 |
| LMArena Japanese | 1356 | 1111 |
| LMArena Korean | 1329 | 1083 |
| LMArena Russian | 1390 | 1169 |
| LMArena Spanish | 1407 | 1168 |
Instruction Following Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 74.2 (#103), Qwen2-72B: 62.0 (#236)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1403 | 1181 |
Long Context Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 43.2 (#99), Qwen2-72B: 36.1 (#230)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1415 | 1193 |
Writing & Preference Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 60.2 (#99), Qwen2-72B: 41.0 (#236)
| Benchmark | Kimi K2 Thinking Turbo | Qwen2-72B |
|---|---|---|
| LMArena Text | 1415 | 1203 |
| LMArena Creative Writing | 1373 | 1181 |
| LMArena Multi-Turn | 1414 | 1195 |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than Qwen2-72B?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 29.5 on the Noometry Index.
Is Kimi K2 Thinking Turbo or Qwen2-72B better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 28.7 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and Qwen2-72B share?
18 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Qwen2-72B has 26.