Model comparison
GPT-4.1 mini vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 33.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 45.5 to 23.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 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-4.1 mini | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 33.5 | 45.4 |
| Released | 2025-04-14 | 2025-11-06 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $1.60 | — |
| Results tracked | 47 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
GPT-4.1 mini: 30.4 (#286), Kimi K2 Thinking Turbo: 38.1 (#166)
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1367 | 1454 |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1322 |
| SciCode | 40.4% | — |
| WeirdML | 37.6% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
Agentic & Tool Use Not comparable
GPT-4.1 mini: 33.0 (#52), Kimi K2 Thinking Turbo: —
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
Reasoning Kimi K2 Thinking Turbo leads
GPT-4.1 mini: 10.9 (#335), Kimi K2 Thinking Turbo: 31.4 (#72)
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 7% | 20% |
| LMArena Hard Prompts | 1349 | 1428 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 48.6% | — |
| ARC-AGI-1 | 3.5% | — |
| CritPt | 0% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LMCA | 21.1% | — |
| Epoch Capabilities Index | 135.01 | — |
Math Kimi K2 Thinking Turbo leads
GPT-4.1 mini: 23.1 (#264), Kimi K2 Thinking Turbo: 45.5 (#62)
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.7% | 83.1% |
| LMArena Math | 1343 | 1429 |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
Knowledge Kimi K2 Thinking Turbo leads
GPT-4.1 mini: 34.7 (#183), Kimi K2 Thinking Turbo: 50.9 (#64)
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 65.8% | 84.2% |
| LMArena Expert | 1338 | 1439 |
| SimpleQA Verified | 12.7% | — |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |
Multimodal Not comparable
GPT-4.1 mini: 35.2 (#77), Kimi K2 Thinking Turbo: —
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Vision | 1181 | — |
Multilingual Kimi K2 Thinking Turbo leads
GPT-4.1 mini: 45.9 (#161), Kimi K2 Thinking Turbo: 51.6 (#104)
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1318 | 1398 |
| LMArena Chinese | 1329 | 1457 |
| LMArena French | 1357 | 1425 |
| LMArena German | 1349 | 1390 |
| LMArena Japanese | 1291 | 1356 |
| LMArena Korean | 1298 | 1329 |
| LMArena Russian | 1324 | 1390 |
| LMArena Spanish | 1319 | 1407 |
Instruction Following Too close to call
GPT-4.1 mini: 73.9 (#113), Kimi K2 Thinking Turbo: 74.2 (#103)
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1332 | 1403 |
| IFEval | 90.4% | — |
Long Context Kimi K2 Thinking Turbo leads
GPT-4.1 mini: 31.8 (#270), Kimi K2 Thinking Turbo: 43.2 (#99)
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1344 | 1415 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Kimi K2 Thinking Turbo leads
GPT-4.1 mini: 48.8 (#193), Kimi K2 Thinking Turbo: 60.2 (#99)
| Benchmark | GPT-4.1 mini | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1341 | 1415 |
| LMArena Creative Writing | 1300 | 1373 |
| LMArena Multi-Turn | 1354 | 1414 |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is GPT-4.1 mini better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 33.5 on the Noometry Index.
Is GPT-4.1 mini or Kimi K2 Thinking Turbo better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 30.4 in the Noometry coding category.
How many benchmarks do GPT-4.1 mini and Kimi K2 Thinking Turbo share?
20 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Kimi K2 Thinking Turbo has 21.