Model comparison
Kimi K2.7 Code vs o3
o3 is the stronger model overall, scoring 47.5 to 43.3 on the Noometry Index. Kimi K2.7 Code costs 2.0× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 10 shared benchmarks.
Summary
- They share 10 benchmarks with published results for both. Kimi K2.7 Code scores higher in 2 categories and o3 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where o3 leads 34.5 to 24.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 54% for Kimi K2.7 Code and 33.3% for o3.
- Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $2 / $8 for o3.
- Kimi K2.7 Code accepts more context: 262K tokens versus 200K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.7 Code | o3 | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 43.3 | 47.5 |
| Released | 2026-06-12 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $0.95 | $2 |
| Output $ / M tokens | $4 | $8 |
| Results tracked | 19 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Kimi K2.7 Code: 42.9 (#95), o3: 46.8 (#64)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| WeirdML | 54.1% | 52.4% |
| ALE-Bench | 886.23 | 933.55 |
| SWE-bench Verified | — | 62.3% |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| GSO | — | 8.8% |
| LMArena Coding | — | 1408 |
| CadEval | — | 74% |
Agentic & Tool Use o3 leads
Kimi K2.7 Code: 24.0 (#122), o3: 34.5 (#44)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| APEX-Agents | 37.6% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| GBAEval | 0.9% | — |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 39.0 (#61), o3: 32.0 (#78)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| SimpleBench | 57.9% | 53.1% |
| CritPt | 10% | 1.4% |
| Chess Puzzles | 21% | 38% |
| Epoch Capabilities Index | 149.97 | 146.86 |
| ARC-AGI-2 | — | 6.5% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| EnigmaEval | — | 13.1% |
| LMArena Hard Prompts | — | 1402 |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| Surface Evolver Bench | 48.8% | — |
| ForecastBench | — | 62.5 |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), o3: 50.2 (#58)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | 33.3% |
| OTIS Mock AIME 2024-2025 | 95.6% | 84.4% |
| FrontierMath Tier 4 | 12.2% | — |
| Omni-MATH | — | 71.4% |
| LMArena Math | — | 1426 |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Kimi K2.7 Code: 53.5 (#57), o3: 54.6 (#52)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| GPQA Diamond | 87.9% | 81.8% |
| SimpleQA Verified | 36.5% | 49.4% |
| Humanity's Last Exam | — | 20.3% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
| LMArena Expert | — | 1402 |
Multimodal Not comparable
Kimi K2.7 Code: —, o3: 41.4 (#36)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Not comparable
Kimi K2.7 Code: —, o3: 51.7 (#105)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| LMArena Non-English | — | 1401 |
| LMArena Chinese | — | 1437 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Russian | — | 1406 |
| LMArena Spanish | — | 1395 |
Instruction Following Not comparable
Kimi K2.7 Code: —, o3: 72.8 (#127)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| IFEval | — | 86.9% |
| LMArena Instruction Following | — | 1368 |
Long Context Not comparable
Kimi K2.7 Code: —, o3: 53.3 (#6)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
| LMArena Longer Query | — | 1372 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, o3: 63.5 (#64)
| Benchmark | Kimi K2.7 Code | o3 |
|---|---|---|
| LMArena Text | — | 1410 |
| LMArena Creative Writing | — | 1359 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Kimi K2.7 Code better than o3?
o3 is the stronger model overall, scoring 47.5 to 43.3 on the Noometry Index. Kimi K2.7 Code costs 2.0× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.7 Code or o3?
Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; o3 lists at $2 and $8.
Is Kimi K2.7 Code or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 42.9 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.7 Code does, with 262K tokens against 200K.
How many benchmarks do Kimi K2.7 Code and o3 share?
10 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and o3 has 63.