Model comparison
Kimi K2 (Jul 2025) vs o1
Kimi K2 (Jul 2025) and o1 score almost the same on the Noometry Index (41.2 vs 40.9), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 4 categories and o1 in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 41.2.
- The biggest single-benchmark swing is Fiction.LiveBench: 66.7% for Kimi K2 (Jul 2025) and 83.3% for o1.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $15 / $60 for o1.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 200K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 (Jul 2025) | o1 | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 41.2 | 40.9 |
| Released | 2025-07-12 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $0.57 | $15 |
| Output $ / M tokens | $2.30 | $60 |
| Results tracked | 42 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Kimi K2 (Jul 2025): 42.4 (#102), o1: 46.1 (#70)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| Aider Polyglot | 59.1% | 61.7% |
| WeirdML | 42.8% | 47.6% |
| LMArena Coding | 1399 | 1367 |
| SWE-bench Verified (bash only) | 63.4% | — |
| GSO | 4.9% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 597.5 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 32.4 (#64), o1: 24.6 (#117)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| METR Time Horizons | 59.2% | 51.1% |
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| Cybench | — | 10% |
Reasoning o1 leads
Kimi K2 (Jul 2025): 23.3 (#179), o1: 27.9 (#111)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| SimpleBench | 26.3% | 41.7% |
| LMArena Hard Prompts | 1384 | 1371 |
| Epoch Capabilities Index | 146.01 | 141.91 |
| Kagi LLM Benchmark | 64.4% | — |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| ForecastBench | 60.2 | — |
| LiveBench | — | 75.7% |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), o1: 36.1 (#175)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| LMArena Math | 1397 | 1388 |
| FrontierMath (Feb 2025 set) | 21.4% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| Omni-MATH | 65.4% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge o1 leads
Kimi K2 (Jul 2025): 37.3 (#157), o1: 41.5 (#110)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| Confabulations | 20.4% | 11.7% |
| LMArena Expert | 1365 | 1361 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 81.9% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, o1: 34.2 (#93)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 49.6 (#130), o1: 48.6 (#142)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| LMArena Non-English | 1372 | 1358 |
| LMArena Chinese | 1415 | 1394 |
| LMArena French | 1379 | 1344 |
| LMArena German | 1387 | 1337 |
| LMArena Japanese | 1349 | 1346 |
| LMArena Korean | 1325 | 1396 |
| LMArena Russian | 1385 | 1356 |
| LMArena Spanish | 1386 | 1345 |
Instruction Following o1 leads
Kimi K2 (Jul 2025): 71.1 (#156), o1: 74.8 (#86)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| LMArena Instruction Following | 1348 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 85% | — |
Long Context o1 leads
Kimi K2 (Jul 2025): 41.2 (#145), o1: 50.3 (#9)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| Fiction.LiveBench | 66.7% | 83.3% |
| LMArena Longer Query | 1353 | 1378 |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), o1: 55.6 (#144)
| Benchmark | Kimi K2 (Jul 2025) | o1 |
|---|---|---|
| LMArena Text | 1380 | 1366 |
| LMArena Creative Writing | 1350 | 1348 |
| Short-Story Creative Writing | 85.6% | 70.2% |
| LMArena Multi-Turn | 1371 | 1369 |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than o1?
Kimi K2 (Jul 2025) and o1 score almost the same on the Noometry Index (41.2 vs 40.9), so choose on price, context window or the category you care about most.
Which is cheaper, Kimi K2 (Jul 2025) or o1?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; o1 lists at $15 and $60.
Is Kimi K2 (Jul 2025) or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 200K.
How many benchmarks do Kimi K2 (Jul 2025) and o1 share?
26 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and o1 has 52.