Model comparison
Kimi K3 vs o3-mini
Kimi K3 is the stronger model overall, scoring 59.5 to 36.7 on the Noometry Index. o3-mini costs 3.1× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Kimi K3 scores higher in 9 categories and o3-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 16.3.
- The biggest single-benchmark swing is ARC-AGI-1: 94.5% for Kimi K3 and 34.5% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 200K.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Kimi K3 | o3-mini | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 59.5 | 36.7 |
| Released | 2026-07-16 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 1.05M | 100K |
| Input $ / M tokens | $3 | $1.10 |
| Output $ / M tokens | $15 | $4.40 |
| Results tracked | 53 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), o3-mini: 40.8 (#132)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| SciCode | 59.5% | 39.8% |
| WeirdML | 82.6% | 43.7% |
| LMArena Coding | 1508 | 1378 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Kimi K3 leads
Kimi K3: 41.8 (#20), o3-mini: 29.6 (#84)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| Cybench | — | 22.5% |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), o3-mini: 16.3 (#305)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| ARC-AGI-2 | 60.4% | 3% |
| SimpleBench | 60.7% | 22.8% |
| ARC-AGI-1 | 94.5% | 34.5% |
| CritPt | 23.4% | 0.3% |
| Chess Puzzles | 39% | 17% |
| LMArena Hard Prompts | 1496 | 1366 |
| Mystery Game Puzzles | 26% | 7% |
| DTBench | 91.2% | 68.8% |
| LMCA | 52.7% | 19% |
| Epoch Capabilities Index | 157.45 | 140.34 |
| ForecastBench | 61.1 | 59.6 |
| NYT Connections (extended) | 93.6% | — |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| Surface Evolver Bench | 95% | — |
| LiveBench | — | 75.9% |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), o3-mini: 28.1 (#244)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 72.2% | 18.6% |
| FrontierMath Tier 4 | 39% | 0% |
| OTIS Mock AIME 2024-2025 | 97.2% | 76.9% |
| LMArena Math | 1491 | 1396 |
| MathArena Final-Answer Competitions | 87.8% | — |
| ProofBench | 87% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), o3-mini: 38.3 (#146)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| GPQA Diamond | 93.1% | 77% |
| SimpleQA Verified | 50.6% | 15.3% |
| LMArena Expert | 1521 | 1364 |
| Confabulations | — | 17.9% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), o3-mini: —
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), o3-mini: 45.7 (#164)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| LMArena Non-English | 1466 | 1319 |
| LMArena Chinese | 1529 | 1379 |
| LMArena French | 1491 | 1334 |
| LMArena German | 1488 | 1303 |
| LMArena Japanese | 1487 | 1286 |
| LMArena Korean | 1458 | 1314 |
| LMArena Russian | 1482 | 1304 |
| LMArena Spanish | 1472 | 1321 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), o3-mini: 75.1 (#72)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1483 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), o3-mini: 33.8 (#256)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1494 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), o3-mini: 50.3 (#182)
| Benchmark | Kimi K3 | o3-mini |
|---|---|---|
| LMArena Text | 1476 | 1337 |
| LMArena Creative Writing | 1454 | 1286 |
| LMArena Multi-Turn | 1488 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Kimi K3 better than o3-mini?
Kimi K3 is the stronger model overall, scoring 59.5 to 36.7 on the Noometry Index. o3-mini costs 3.1× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or o3-mini better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 200K.
How many benchmarks do Kimi K3 and o3-mini share?
34 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and o3-mini has 51.