Model comparison
Kimi K2.7 Code vs Qwen2.5-VL 72B Instruct
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 29.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Kimi K2.7 Code leads 39.0 to 20.7.
- Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Kimi K2.7 Code accepts more context: 262K tokens versus 131K.
Side by side
| Kimi K2.7 Code | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 43.3 | 29.9 |
| Released | 2026-06-12 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $0.95 | $2.80 |
| Output $ / M tokens | $4 | $8.40 |
| Results tracked | 19 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Kimi K2.7 Code: 42.9 (#95), Qwen2.5-VL 72B Instruct: —
| Benchmark | Kimi K2.7 Code | Qwen2.5-VL 72B Instruct |
|---|---|---|
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| WeirdML | 54.1% | — |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Kimi K2.7 Code leads
Kimi K2.7 Code: 24.0 (#122), Qwen2.5-VL 72B Instruct: 18.6 (#144)
| Benchmark | Kimi K2.7 Code | Qwen2.5-VL 72B Instruct |
|---|---|---|
| APEX-Agents | 37.6% | — |
| OSWorld | — | 5% |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 39.0 (#61), Qwen2.5-VL 72B Instruct: 20.7 (#233)
| Benchmark | Kimi K2.7 Code | Qwen2.5-VL 72B Instruct |
|---|---|---|
| SimpleBench | 57.9% | — |
| Kagi LLM Benchmark | — | 36% |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| Surface Evolver Bench | 48.8% | — |
| Epoch Capabilities Index | 149.97 | — |
Math Not comparable
Kimi K2.7 Code: 52.9 (#48), Qwen2.5-VL 72B Instruct: —
| Benchmark | Kimi K2.7 Code | Qwen2.5-VL 72B Instruct |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
Knowledge Not comparable
Kimi K2.7 Code: 53.5 (#57), Qwen2.5-VL 72B Instruct: —
| Benchmark | Kimi K2.7 Code | Qwen2.5-VL 72B Instruct |
|---|---|---|
| GPQA Diamond | 87.9% | — |
| SimpleQA Verified | 36.5% | — |
Multimodal Not comparable
Kimi K2.7 Code: —, Qwen2.5-VL 72B Instruct: 33.5 (#97)
| Benchmark | Kimi K2.7 Code | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | — | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Frequently asked questions
Is Kimi K2.7 Code better than Qwen2.5-VL 72B Instruct?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 29.9 on the Noometry Index.
Which is cheaper, Kimi K2.7 Code or Qwen2.5-VL 72B Instruct?
Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Kimi K2.7 Code does, with 262K tokens against 131K.
How many benchmarks do Kimi K2.7 Code and Qwen2.5-VL 72B Instruct share?
0 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.