Model comparison
Kimi K2.7 Code vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.3 on the Noometry Index. Kimi K2.7 Code costs 1.8× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Kimi K2.7 Code scores higher in 0 categories and Qwen3.8 Max in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen3.8 Max leads 45.4 to 24.0.
- The biggest single-benchmark swing is FrontierMath Tier 4: 12.2% for Kimi K2.7 Code and 46.3% for Qwen3.8 Max.
- Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 262K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.7 Code | Qwen3.8 Max | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 43.3 | 56.8 |
| Released | 2026-06-12 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.95 | $2 |
| Output $ / M tokens | $4 | $6 |
| Results tracked | 19 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Kimi K2.7 Code: 42.9 (#95), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| DeepSWE | 30.5% | 57.5% |
| LMArena WebDev | 1473 | 1674 |
| SciCode | 47.5% | 53.2% |
| FrontierCode | 30.1% | — |
| FrontierSWE | — | 17.8% |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1502 |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Qwen3.8 Max leads
Kimi K2.7 Code: 24.0 (#122), Qwen3.8 Max: 45.4 (#14)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | 37.6% | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GBAEval | 0.9% | — |
| GDP.pdf | — | 23.2% |
| Vending-Bench 2 | 5,083 | — |
Reasoning Qwen3.8 Max leads
Kimi K2.7 Code: 39.0 (#61), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| CritPt | 10% | 20% |
| Chess Puzzles | 21% | 40% |
| Epoch Capabilities Index | 149.97 | 156.41 |
| SimpleBench | 57.9% | — |
| NYT Connections (extended) | — | 88.3% |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Surface Evolver Bench | 48.8% | — |
Math Qwen3.8 Max leads
Kimi K2.7 Code: 52.9 (#48), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | 74.7% |
| FrontierMath Tier 4 | 12.2% | 46.3% |
| OTIS Mock AIME 2024-2025 | 95.6% | 100% |
| ProofBench | — | 58% |
| LMArena Math | — | 1499 |
Knowledge Qwen3.8 Max leads
Kimi K2.7 Code: 53.5 (#57), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 87.9% | 92.7% |
| SimpleQA Verified | 36.5% | 47.3% |
| LMArena Expert | — | 1507 |
Multimodal Not comparable
Kimi K2.7 Code: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Kimi K2.7 Code: —, Qwen3.8 Max: 56.7 (#18)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1472 |
| LMArena Chinese | — | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Russian | — | 1481 |
| LMArena Spanish | — | 1492 |
Instruction Following Not comparable
Kimi K2.7 Code: —, Qwen3.8 Max: 77.6 (#17)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1479 |
Long Context Not comparable
Kimi K2.7 Code: —, Qwen3.8 Max: 45.6 (#31)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Qwen3.8 Max: 67.1 (#30)
| Benchmark | Kimi K2.7 Code | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1483 |
| LMArena Creative Writing | — | 1479 |
| LMArena Multi-Turn | — | 1489 |
Frequently asked questions
Is Kimi K2.7 Code better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.3 on the Noometry Index. Kimi K2.7 Code costs 1.8× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.7 Code or Qwen3.8 Max?
Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Kimi K2.7 Code or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 42.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 262K.
How many benchmarks do Kimi K2.7 Code and Qwen3.8 Max share?
12 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Qwen3.8 Max has 39.