Model comparison
GPT-4o mini vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 25.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 45.5 to 9.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 83.1% for Kimi K2 Thinking Turbo.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 25.4 | 45.4 |
| Released | 2024-07-18 | 2025-11-06 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 60 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
GPT-4o mini: 21.6 (#330), Kimi K2 Thinking Turbo: 38.1 (#166)
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1290 | 1454 |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1322 |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.2 (#95), Kimi K2 Thinking Turbo: —
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Kimi K2 Thinking Turbo leads
GPT-4o mini: 8.7 (#343), Kimi K2 Thinking Turbo: 31.4 (#72)
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 0% | 20% |
| LMArena Hard Prompts | 1267 | 1428 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Epoch Capabilities Index | 126.56 | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Kimi K2 Thinking Turbo leads
GPT-4o mini: 9.9 (#307), Kimi K2 Thinking Turbo: 45.5 (#62)
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 83.1% |
| LMArena Math | 1267 | 1429 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge Kimi K2 Thinking Turbo leads
GPT-4o mini: 17.7 (#279), Kimi K2 Thinking Turbo: 50.9 (#64)
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 37.7% | 84.2% |
| LMArena Expert | 1235 | 1439 |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.3 (#117), Kimi K2 Thinking Turbo: —
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Kimi K2 Thinking Turbo leads
GPT-4o mini: 42.2 (#194), Kimi K2 Thinking Turbo: 51.6 (#104)
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1266 | 1398 |
| LMArena Chinese | 1264 | 1457 |
| LMArena French | 1296 | 1425 |
| LMArena German | 1272 | 1390 |
| LMArena Japanese | 1216 | 1356 |
| LMArena Korean | 1195 | 1329 |
| LMArena Russian | 1275 | 1390 |
| LMArena Spanish | 1276 | 1407 |
Instruction Following Kimi K2 Thinking Turbo leads
GPT-4o mini: 62.1 (#234), Kimi K2 Thinking Turbo: 74.2 (#103)
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1259 | 1403 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Kimi K2 Thinking Turbo leads
GPT-4o mini: 39.1 (#181), Kimi K2 Thinking Turbo: 43.2 (#99)
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1289 | 1415 |
Writing & Preference Kimi K2 Thinking Turbo leads
GPT-4o mini: 39.7 (#243), Kimi K2 Thinking Turbo: 60.2 (#99)
| Benchmark | GPT-4o mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1286 | 1415 |
| LMArena Creative Writing | 1268 | 1373 |
| LMArena Multi-Turn | 1285 | 1414 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 25.4 on the Noometry Index.
Is GPT-4o mini or Kimi K2 Thinking Turbo better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 21.6 in the Noometry coding category.
How many benchmarks do GPT-4o mini and Kimi K2 Thinking Turbo share?
20 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Kimi K2 Thinking Turbo has 21.