# GPT-5 vs Kimi K2.7 Code

> GPT-5 is the stronger model overall, scoring 50.9 to 43.0 on the Noometry Index. Kimi K2.7 Code costs 2.0× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-vs-kimi-k2-7-code
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. GPT-5 scores higher in 5 categories and Kimi K2.7 Code in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5 leads 33.0 to 23.9.
- The biggest single-benchmark swing is Chess Puzzles: 37% for GPT-5 and 21% for Kimi K2.7 Code.
- Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $1.25 / $10 for GPT-5.
- GPT-5 accepts more context: 400K tokens versus 262K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 50.9 | 43.0 |
| Rank | 37 | 90 |
| Context | 400K | 262K |
| Input $/M | $1.25 | $0.95 |
| Output $/M | $10 | $4 |
| Weights | Proprietary | Open |

## Coding

- GPT-5: 50.7 (#39)
- Kimi K2.7 Code: 42.4 (#92)

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| LMArena WebDev | 1417 | 1473 |
| SciCode | 42.9% | 47.5% |
| WeirdML | 60.7% | 54.1% |
| ALE-Bench | 1,162 | 886.23 |
| SWE-bench Verified | 73.6% | — |
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| SWE-bench Verified (bash only) | 65% | — |
| Aider Polyglot | 88% | — |
| GSO | 6.9% | — |
| LMArena Coding | 1436 | — |
| AlgoTune | 1.67 | — |

## Agentic & Tool Use

- GPT-5: 33.0 (#53)
- Kimi K2.7 Code: 23.9 (#115)

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| APEX-Agents | — | 37.6% |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| GBAEval | — | 0.9% |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |
| Vending-Bench 2 | — | 5,083 |

## Reasoning

- GPT-5: 38.3 (#55)
- Kimi K2.7 Code: 38.2 (#56)

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| SimpleBench | 56.7% | 57.9% |
| CritPt | 12.6% | 10% |
| Chess Puzzles | 37% | 21% |
| Epoch Capabilities Index | 150 | 150.01 |
| ARC-AGI-2 | 9.9% | — |
| Kagi LLM Benchmark | 72.7% | — |
| ARC-AGI-1 | 65.7% | — |
| EnigmaEval | 10.5% | — |
| EBR-Bench | 12.7% | — |
| LMArena Hard Prompts | 1415 | — |
| Mystery Game Puzzles | 23% | — |
| DTBench | 90.7% | — |
| LMCA | 40% | — |
| Surface Evolver Bench | — | 48.8% |
| ForecastBench | 61.4 | — |

## Math

- GPT-5: 54.6 (#36)
- Kimi K2.7 Code: 52.6 (#39)

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.4% | 54% |
| FrontierMath Tier 4 | 22% | 12.2% |
| OTIS Mock AIME 2024-2025 | 91.4% | 95.6% |
| ProofBench | 18% | — |
| Omni-MATH | 64.7% | — |
| LMArena Math | 1406 | — |
| MATH Level 5 | 98.1% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GPT-5: 56.5 (#37)
- Kimi K2.7 Code: 53.6 (#51)

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 86.2% | 87.9% |
| SimpleQA Verified | 50.1% | 36.5% |
| Humanity's Last Exam | 25.3% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |
| LMArena Expert | 1420 | — |

## Multimodal

- GPT-5: 46.1 (#12)
- Kimi K2.7 Code: —

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| LMArena Vision | 1232 | — |
| GeoBench | 81% | — |
| VPCT | 66% | — |

## Multilingual

- GPT-5: 51.5 (#105)
- Kimi K2.7 Code: —

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| LMArena Non-English | 1397 | — |
| LMArena Chinese | 1423 | — |
| LMArena French | 1409 | — |
| LMArena German | 1415 | — |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1361 | — |
| LMArena Russian | 1406 | — |
| LMArena Spanish | 1398 | — |

## Instruction Following

- GPT-5: 74.0 (#107)
- Kimi K2.7 Code: —

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| IFEval | 87.5% | — |
| LMArena Instruction Following | 1388 | — |

## Long Context

- GPT-5: 69.5 (#2)
- Kimi K2.7 Code: —

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | 1399 | — |

## Writing & Preference

- GPT-5: 63.5 (#63)
- Kimi K2.7 Code: —

| Benchmark | GPT-5 | Kimi K2.7 Code |
|---|---|---|
| LMArena Text | 1406 | — |
| LMArena Creative Writing | 1365 | — |
| Short-Story Creative Writing | 86% | — |
| EQ-Bench Creative Writing | 1627 | — |
| WildBench | 85.7% | — |
| LMArena Multi-Turn | 1426 | — |

## FAQ

### Is GPT-5 better than Kimi K2.7 Code?

GPT-5 is the stronger model overall, scoring 50.9 to 43.0 on the Noometry Index. Kimi K2.7 Code costs 2.0× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

### Which is cheaper, GPT-5 or Kimi K2.7 Code?

Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; GPT-5 lists at $1.25 and $10.

### Is GPT-5 or Kimi K2.7 Code better for coding?

GPT-5 scores higher on coding benchmarks: 50.7 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 does, with 400K tokens against 262K.

### How many benchmarks do GPT-5 and Kimi K2.7 Code share?

13 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and Kimi K2.7 Code has 19.