Model comparison
Kimi K2 (Jul 2025) vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 35× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Summary
- They share 8 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 2 categories and o3-pro in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 41.2.
- The biggest single-benchmark swing is Fiction.LiveBench: 66.7% for Kimi K2 (Jul 2025) and 97.2% for o3-pro.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $20 / $80 for o3-pro.
- 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) | o3-pro | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 41.2 | 42.9 |
| Released | 2025-07-12 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $0.57 | $20 |
| Output $ / M tokens | $2.30 | $80 |
| Results tracked | 42 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Kimi K2 (Jul 2025): 42.4 (#102), o3-pro: 55.5 (#24)
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| Aider Polyglot | 59.1% | 84.9% |
| WeirdML | 42.8% | 58.2% |
| SWE-bench Verified (bash only) | 63.4% | — |
| GSO | 4.9% | — |
| LMArena Coding | 1399 | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), o3-pro: —
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Too close to call
Kimi K2 (Jul 2025): 23.3 (#179), o3-pro: 23.8 (#171)
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| Kagi LLM Benchmark | 64.4% | 72.1% |
| Epoch Capabilities Index | 146.01 | 147.42 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | 26.3% | — |
| ARC-AGI-1 | — | 59.3% |
| LMArena Hard Prompts | 1384 | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
| ForecastBench | 60.2 | — |
Math Not comparable
Kimi K2 (Jul 2025): 42.7 (#83), o3-pro: —
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| Omni-MATH | 65.4% | — |
| LMArena Math | 1397 | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 37.3 (#157), o3-pro: 29.5 (#238)
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| Confabulations | 20.4% | 14.2% |
| Vectara Hallucination Rate | 17.9% | 23.3% |
| MMLU-Pro | 81.9% | — |
| GPQA (HELM) | 65.3% | — |
| LMArena Expert | 1365 | — |
Multilingual Not comparable
Kimi K2 (Jul 2025): 49.6 (#130), o3-pro: —
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| LMArena Non-English | 1372 | — |
| LMArena Chinese | 1415 | — |
| LMArena French | 1379 | — |
| LMArena German | 1387 | — |
| LMArena Japanese | 1349 | — |
| LMArena Korean | 1325 | — |
| LMArena Russian | 1385 | — |
| LMArena Spanish | 1386 | — |
Instruction Following Not comparable
Kimi K2 (Jul 2025): 71.1 (#156), o3-pro: —
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| IFEval | 85% | — |
| LMArena Instruction Following | 1348 | — |
Long Context o3-pro leads
Kimi K2 (Jul 2025): 41.2 (#145), o3-pro: 72.2 (#1)
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| Fiction.LiveBench | 66.7% | 97.2% |
| CL-bench | 17.6% | — |
| LMArena Longer Query | 1353 | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), o3-pro: 57.1 (#133)
| Benchmark | Kimi K2 (Jul 2025) | o3-pro |
|---|---|---|
| Short-Story Creative Writing | 85.6% | 84.4% |
| LMArena Text | 1380 | — |
| LMArena Creative Writing | 1350 | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
| LMArena Multi-Turn | 1371 | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 35× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, Kimi K2 (Jul 2025) or o3-pro?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; o3-pro lists at $20 and $80.
Is Kimi K2 (Jul 2025) or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 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 o3-pro share?
8 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and o3-pro has 12.