Model comparison
GPT-4.5 vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 36.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and Kimi K2.5 Instant in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.5 Instant leads 28.5 to 14.1.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Kimi K2.5 Instant | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 36.9 | 42.9 |
| Released | 2025-02-27 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.5: 41.8 (#102), Kimi K2.5 Instant: 42.3 (#95)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1397 | 1483 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1404 |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.6 (#92), Kimi K2.5 Instant: —
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Kimi K2.5 Instant leads
GPT-4.5: 14.1 (#320), Kimi K2.5 Instant: 28.5 (#88)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1443 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Kimi K2.5 Instant leads
GPT-4.5: 31.0 (#200), Kimi K2.5 Instant: 36.6 (#105)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1412 | 1443 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Kimi K2.5 Instant leads
GPT-4.5: 32.4 (#205), Kimi K2.5 Instant: 39.5 (#121)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1394 | 1438 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal Kimi K2.5 Instant leads
GPT-4.5: 37.0 (#68), Kimi K2.5 Instant: 39.5 (#47)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | 1195 | 1254 |
| VPCT | 45% | — |
Multilingual Too close to call
GPT-4.5: 52.7 (#78), Kimi K2.5 Instant: 52.2 (#89)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1413 | 1406 |
| LMArena Chinese | 1421 | 1450 |
| LMArena French | 1417 | 1403 |
| LMArena German | 1457 | 1413 |
| LMArena Korean | 1392 | 1378 |
| LMArena Russian | 1419 | 1404 |
| LMArena Japanese | 1416 | — |
| LMArena Spanish | — | 1448 |
Instruction Following Kimi K2.5 Instant leads
GPT-4.5: 72.8 (#129), Kimi K2.5 Instant: 75.5 (#61)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1404 | 1430 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Kimi K2.5 Instant leads
GPT-4.5: 40.4 (#150), Kimi K2.5 Instant: 43.8 (#82)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1406 | 1435 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Kimi K2.5 Instant leads
GPT-4.5: 57.1 (#129), Kimi K2.5 Instant: 60.8 (#91)
| Benchmark | GPT-4.5 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1417 | 1420 |
| LMArena Creative Writing | 1394 | 1379 |
| LMArena Multi-Turn | 1444 | 1427 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 36.9 on the Noometry Index.
Is GPT-4.5 or Kimi K2.5 Instant better for coding?
They score almost the same on coding (41.8 vs 42.3); test both on your own repository before choosing.
How many benchmarks do GPT-4.5 and Kimi K2.5 Instant share?
16 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Kimi K2.5 Instant has 18.