Model comparison
GPT-5.4 nano vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 41.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-5.4 nano scores higher in 3 categories and Kimi K2.5 Instant in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.5 Instant leads 29.7 to 23.7.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 nano | Kimi K2.5 Instant | |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 41.9 | 43.6 |
| Released | 2026-03-17 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.25 | — |
| Results tracked | 40 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
GPT-5.4 nano: 43.6 (#84), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1405 | 1484 |
| LMArena WebDev | — | 1404 |
| SciCode | 46.9% | — |
| WeirdML | 49.2% | — |
| ALE-Bench | 1,005 | — |
Reasoning Kimi K2.5 Instant leads
GPT-5.4 nano: 23.7 (#173), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1381 | 1443 |
| ARC-AGI-2 | 5.7% | — |
| Kagi LLM Benchmark | 39.7% | — |
| ARC-AGI-1 | 51.5% | — |
| CritPt | 9.3% | — |
| Chess Puzzles | 30% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 145.81 | — |
| ForecastBench | 57.3 | — |
Math GPT-5.4 nano leads
GPT-5.4 nano: 40.9 (#88), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1406 | 1442 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 5% | — |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5.4 nano leads
GPT-5.4 nano: 41.9 (#103), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1396 | 1440 |
| GPQA Diamond | 78.5% | — |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 3.1% | — |
Multimodal Kimi K2.5 Instant leads
GPT-5.4 nano: 36.7 (#78), Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | 1196 | 1254 |
Multilingual Kimi K2.5 Instant leads
GPT-5.4 nano: 48.6 (#140), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1359 | 1406 |
| LMArena Chinese | 1392 | 1449 |
| LMArena French | 1396 | 1403 |
| LMArena German | 1367 | 1413 |
| LMArena Korean | 1320 | 1378 |
| LMArena Russian | 1363 | 1404 |
| LMArena Spanish | 1371 | 1447 |
| LMArena Japanese | 1343 | — |
Instruction Following Kimi K2.5 Instant leads
GPT-5.4 nano: 71.9 (#144), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1362 | 1430 |
Long Context Kimi K2.5 Instant leads
GPT-5.4 nano: 41.6 (#137), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1366 | 1435 |
Writing & Preference Kimi K2.5 Instant leads
GPT-5.4 nano: 55.7 (#142), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | GPT-5.4 nano | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1372 | 1420 |
| LMArena Creative Writing | 1314 | 1381 |
| LMArena Multi-Turn | 1382 | 1427 |
Frequently asked questions
Is GPT-5.4 nano better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 41.9 on the Noometry Index.
Is GPT-5.4 nano or Kimi K2.5 Instant better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 42.6 in the Noometry coding category.
How many benchmarks do GPT-5.4 nano and Kimi K2.5 Instant share?
17 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Kimi K2.5 Instant has 18.