Model comparison
GPT-4.5 vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 36.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and Kimi K2 (Jul 2025) in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 40.1 to 31.0.
- The biggest single-benchmark swing is Aider Polyglot: 44.9% for GPT-4.5 and 59.1% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 36.9 | 40.9 |
| Released | 2025-02-27 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.57 |
| Output $ / M tokens | — | $2.30 |
| Results tracked | 42 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
GPT-4.5: 41.8 (#102), Kimi K2 (Jul 2025): 43.1 (#83)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Aider Polyglot | 44.9% | 59.1% |
| WeirdML | 39.4% | 42.8% |
| LMArena Coding | 1397 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| GSO | — | 4.9% |
| LiveBench Coding | 75.2% | — |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
GPT-4.5: 27.6 (#92), Kimi K2 (Jul 2025): 32.2 (#59)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| Cybench | 17.5% | — |
| METR Time Horizons | — | 59.2% |
Reasoning Kimi K2 (Jul 2025) leads
GPT-4.5: 14.1 (#320), Kimi K2 (Jul 2025): 22.7 (#173)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 34.5% | 26.3% |
| LMArena Hard Prompts | 1404 | 1384 |
| Epoch Capabilities Index | 136.74 | 146.02 |
| ForecastBench | 61.7 | 60.2 |
| ARC-AGI-2 | 0.8% | — |
| Kagi LLM Benchmark | — | 64.4% |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| LiveBench | 69% | — |
Math Kimi K2 (Jul 2025) leads
GPT-4.5: 31.0 (#200), Kimi K2 (Jul 2025): 40.1 (#81)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1412 | 1396 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| Omni-MATH | — | 65.4% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Kimi K2 (Jul 2025) leads
GPT-4.5: 32.4 (#205), Kimi K2 (Jul 2025): 36.9 (#153)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Confabulations | 13.6% | 20.4% |
| LMArena Expert | 1394 | 1363 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | — | 81.9% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
Multimodal Not comparable
GPT-4.5: 37.0 (#68), Kimi K2 (Jul 2025): —
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.7 (#78), Kimi K2 (Jul 2025): 49.8 (#125)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1413 | 1372 |
| LMArena Chinese | 1421 | 1416 |
| LMArena French | 1417 | 1379 |
| LMArena German | 1457 | 1386 |
| LMArena Japanese | 1416 | 1349 |
| LMArena Korean | 1392 | 1324 |
| LMArena Russian | 1419 | 1384 |
| LMArena Spanish | — | 1383 |
Instruction Following GPT-4.5 leads
GPT-4.5: 72.8 (#129), Kimi K2 (Jul 2025): 71.3 (#151)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1404 | 1347 |
| LiveBench Instruction Following | 72.3% | — |
| IFEval | — | 85% |
Long Context Too close to call
GPT-4.5: 40.4 (#150), Kimi K2 (Jul 2025): 41.2 (#140)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 63.9% | 66.7% |
| LMArena Longer Query | 1406 | 1353 |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
GPT-4.5: 57.1 (#129), Kimi K2 (Jul 2025): 62.5 (#76)
| Benchmark | GPT-4.5 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1417 | 1380 |
| LMArena Creative Writing | 1394 | 1349 |
| Short-Story Creative Writing | 75.6% | 85.6% |
| EQ-Bench Creative Writing | 1258 | 1666 |
| LMArena Multi-Turn | 1444 | 1371 |
| WildBench | — | 86.2% |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 36.9 on the Noometry Index.
Is GPT-4.5 or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 41.8 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Kimi K2 (Jul 2025) share?
25 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Kimi K2 (Jul 2025) has 42.