Model comparison
Kimi K2.7 Code vs Qwen3.5 35B-A3B
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 2.5× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and Qwen3.5 35B-A3B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.7 Code leads 39.0 to 24.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 70% for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
Side by side
| Kimi K2.7 Code | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 43.3 | 42.0 |
| Released | 2026-06-12 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 66K |
| Input $ / M tokens | $0.95 | $0.25 |
| Output $ / M tokens | $4 | $2 |
| Results tracked | 19 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
Kimi K2.7 Code: 42.9 (#95), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena WebDev | 1473 | 1254 |
| SciCode | 47.5% | 29.3% |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1410 |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Not comparable
Kimi K2.7 Code: 24.0 (#122), Qwen3.5 35B-A3B: —
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 39.0 (#61), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 10% | 0.6% |
| Chess Puzzles | 21% | 10% |
| Epoch Capabilities Index | 149.97 | 142.52 |
| SimpleBench | 57.9% | — |
| LMArena Hard Prompts | — | 1400 |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Surface Evolver Bench | 48.8% | — |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 70% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| MathArena Final-Answer Competitions | — | 56% |
| LMArena Math | — | 1404 |
Knowledge Kimi K2.7 Code leads
Kimi K2.7 Code: 53.5 (#57), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 87.9% | 83.5% |
| SimpleQA Verified | 36.5% | — |
| Vectara Hallucination Rate | — | 10.5% |
| LMArena Expert | — | 1408 |
Multilingual Not comparable
Kimi K2.7 Code: —, Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | — | 1378 |
| LMArena Chinese | — | 1457 |
| LMArena French | — | 1412 |
| LMArena German | — | 1367 |
| LMArena Japanese | — | 1325 |
| LMArena Korean | — | 1356 |
| LMArena Russian | — | 1376 |
| LMArena Spanish | — | 1392 |
Instruction Following Not comparable
Kimi K2.7 Code: —, Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | — | 1379 |
Long Context Not comparable
Kimi K2.7 Code: —, Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | — | 1389 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Kimi K2.7 Code | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | — | 1395 |
| LMArena Creative Writing | — | 1346 |
| LMArena Multi-Turn | — | 1390 |
Frequently asked questions
Is Kimi K2.7 Code better than Qwen3.5 35B-A3B?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 2.5× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.7 Code or Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.
Is Kimi K2.7 Code or Qwen3.5 35B-A3B better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2.7 Code and Qwen3.5 35B-A3B share?
7 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Qwen3.5 35B-A3B has 28.