Model comparison
GPT-5 Nano vs Kimi K2.7 Code
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 33.5 on the Noometry Index. GPT-5 Nano costs 12× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Summary
- They share 9 benchmarks with published results for both. GPT-5 Nano scores higher in 1 category and Kimi K2.7 Code in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.7 Code leads 52.9 to 29.4.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 20% for GPT-5 Nano and 54% for Kimi K2.7 Code.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- GPT-5 Nano accepts more context: 400K tokens versus 262K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Kimi K2.7 Code | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 33.5 | 43.3 |
| Released | 2025-08-07 | 2026-06-12 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.05 | $0.95 |
| Output $ / M tokens | $0.40 | $4 |
| Results tracked | 49 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
GPT-5 Nano: 33.6 (#254), Kimi K2.7 Code: 42.9 (#95)
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| WeirdML | 38.1% | 54.1% |
| ALE-Bench | 718.67 | 886.23 |
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena WebDev | — | 1473 |
| SciCode | — | 47.5% |
| LMArena Coding | 1351 | — |
Agentic & Tool Use GPT-5 Nano leads
GPT-5 Nano: 25.8 (#106), Kimi K2.7 Code: 24.0 (#122)
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| APEX-Agents | — | 37.6% |
| Berkeley Function Calling Leaderboard | 51.5% | — |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 5,083 |
Reasoning Kimi K2.7 Code leads
GPT-5 Nano: 16.3 (#306), Kimi K2.7 Code: 39.0 (#61)
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| Chess Puzzles | 27% | 21% |
| Epoch Capabilities Index | 139.38 | 149.97 |
| ARC-AGI-2 | 2.6% | — |
| SimpleBench | — | 57.9% |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 10% |
| LMArena Hard Prompts | 1328 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Surface Evolver Bench | — | 48.8% |
| ForecastBench | 59.1 | — |
Math Kimi K2.7 Code leads
GPT-5 Nano: 29.4 (#241), Kimi K2.7 Code: 52.9 (#48)
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20% | 54% |
| FrontierMath Tier 4 | 2.4% | 12.2% |
| OTIS Mock AIME 2024-2025 | 81.1% | 95.6% |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| LMArena Math | 1317 | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Kimi K2.7 Code leads
GPT-5 Nano: 35.9 (#178), Kimi K2.7 Code: 53.5 (#57)
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 69.4% | 87.9% |
| SimpleQA Verified | 11.7% | 36.5% |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
| LMArena Expert | 1321 | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Kimi K2.7 Code: —
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual Not comparable
GPT-5 Nano: 45.3 (#172), Kimi K2.7 Code: —
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1356 | — |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Russian | 1296 | — |
| LMArena Spanish | 1360 | — |
Instruction Following Not comparable
GPT-5 Nano: 75.0 (#79), Kimi K2.7 Code: —
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| IFEval | 93.2% | — |
| LMArena Instruction Following | 1306 | — |
Long Context Not comparable
GPT-5 Nano: 31.3 (#281), Kimi K2.7 Code: —
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| Fiction.LiveBench | 44.4% | — |
| LMArena Longer Query | 1312 | — |
Writing & Preference Not comparable
GPT-5 Nano: 39.1 (#249), Kimi K2.7 Code: —
| Benchmark | GPT-5 Nano | Kimi K2.7 Code |
|---|---|---|
| LMArena Text | 1320 | — |
| LMArena Creative Writing | 1249 | — |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
| LMArena Multi-Turn | 1311 | — |
Frequently asked questions
Is GPT-5 Nano better than Kimi K2.7 Code?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 33.5 on the Noometry Index. GPT-5 Nano costs 12× 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, GPT-5 Nano or Kimi K2.7 Code?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.
Is GPT-5 Nano or Kimi K2.7 Code better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Nano and Kimi K2.7 Code share?
9 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Kimi K2.7 Code has 19.