Model comparison
GPT-5 Mini vs Kimi K2 (Jul 2025)
GPT-5 Mini and Kimi K2 (Jul 2025) score almost the same on the Noometry Index (41.8 vs 41.2), so choose on price, context window or the category you care about most.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. GPT-5 Mini scores higher in 5 categories and Kimi K2 (Jul 2025) in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Mini leads 45.6 to 37.3.
- The biggest single-benchmark swing is GPQA (HELM): 75.6% for GPT-5 Mini and 65.3% for Kimi K2 (Jul 2025).
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- GPT-5 Mini accepts more context: 400K tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 41.8 | 41.2 |
| Released | 2025-08-07 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.25 | $0.57 |
| Output $ / M tokens | $2 | $2.30 |
| Results tracked | 60 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
GPT-5 Mini: 40.1 (#146), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 59.8% | 63.4% |
| WeirdML | 52.7% | 42.8% |
| LMArena Coding | 1406 | 1399 |
| ALE-Bench | 799.77 | 597.5 |
| SWE-bench Verified | 64.7% | — |
| Aider Polyglot | — | 59.1% |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| GSO | — | 4.9% |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
GPT-5 Mini: 31.1 (#70), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | 34.8% | 35.7% |
| Berkeley Function Calling Leaderboard | 55.5% | 59.1% |
| METR Time Horizons | — | 59.2% |
| Vending-Bench 2 | -31.18 | — |
Reasoning Too close to call
GPT-5 Mini: 23.9 (#168), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 64.4% |
| LMArena Hard Prompts | 1380 | 1384 |
| Epoch Capabilities Index | 145.52 | 146.01 |
| ForecastBench | 61 | 60.2 |
| ARC-AGI-2 | 4.4% | — |
| SimpleBench | — | 26.3% |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 72.2% | 65.4% |
| LMArena Math | 1378 | 1397 |
| FrontierMath (Feb 2025 set) | 27.2% | 21.4% |
| FrontierMath Tier 4 (v1) | 6.3% | 0% |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 97.8% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 83.5% | 81.9% |
| Confabulations | 13.3% | 20.4% |
| Vectara Hallucination Rate | 12.9% | 17.9% |
| GPQA (HELM) | 75.6% | 65.3% |
| LMArena Expert | 1379 | 1365 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Kimi K2 (Jul 2025): —
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual Too close to call
GPT-5 Mini: 48.9 (#137), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1363 | 1372 |
| LMArena Chinese | 1385 | 1415 |
| LMArena French | 1386 | 1379 |
| LMArena German | 1366 | 1387 |
| LMArena Japanese | 1341 | 1349 |
| LMArena Korean | 1308 | 1325 |
| LMArena Russian | 1362 | 1385 |
| LMArena Spanish | 1355 | 1386 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 92.7% | 85% |
| LMArena Instruction Following | 1357 | 1348 |
Long Context Too close to call
GPT-5 Mini: 41.9 (#132), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 69.4% | 66.7% |
| LMArena Longer Query | 1355 | 1353 |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
GPT-5 Mini: 55.2 (#148), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | GPT-5 Mini | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1373 | 1380 |
| LMArena Creative Writing | 1325 | 1350 |
| Short-Story Creative Writing | 83.1% | 85.6% |
| EQ-Bench Creative Writing | 1313 | 1666 |
| WildBench | 85.5% | 86.2% |
| LMArena Multi-Turn | 1363 | 1371 |
Frequently asked questions
Is GPT-5 Mini better than Kimi K2 (Jul 2025)?
GPT-5 Mini and Kimi K2 (Jul 2025) score almost the same on the Noometry Index (41.8 vs 41.2), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5 Mini or Kimi K2 (Jul 2025)?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is GPT-5 Mini or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Mini and Kimi K2 (Jul 2025) share?
37 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Kimi K2 (Jul 2025) has 42.