Model comparison
Gemma 3 4B vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 28.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Kimi K2.5 Instant in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 Instant leads 40.2 to 11.8.
Side by side
| Gemma 3 4B | Kimi K2.5 Instant | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 28.1 | 43.6 |
| Released | 2025-03-12 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
Gemma 3 4B: 35.9 (#215), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1230 | 1484 |
| LMArena WebDev | — | 1404 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Kimi K2.5 Instant: —
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Kimi K2.5 Instant leads
Gemma 3 4B: 13.2 (#335), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1443 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Kimi K2.5 Instant leads
Gemma 3 4B: 16.8 (#292), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1239 | 1442 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Kimi K2.5 Instant leads
Gemma 3 4B: 11.8 (#299), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1223 | 1440 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multimodal Not comparable
Gemma 3 4B: —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Kimi K2.5 Instant leads
Gemma 3 4B: 42.5 (#194), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1273 | 1406 |
| LMArena German | 1281 | 1413 |
| LMArena Russian | 1294 | 1404 |
| LMArena Chinese | — | 1449 |
| LMArena French | — | 1403 |
| LMArena Korean | — | 1378 |
| LMArena Spanish | — | 1447 |
Instruction Following Kimi K2.5 Instant leads
Gemma 3 4B: 65.2 (#225), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1239 | 1430 |
Long Context Kimi K2.5 Instant leads
Gemma 3 4B: 38.7 (#194), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1273 | 1435 |
Writing & Preference Kimi K2.5 Instant leads
Gemma 3 4B: 42.0 (#239), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | Gemma 3 4B | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1291 | 1420 |
| LMArena Creative Writing | 1271 | 1381 |
| LMArena Multi-Turn | 1255 | 1427 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Kimi K2.5 Instant better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 35.9 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Kimi K2.5 Instant share?
12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Kimi K2.5 Instant has 18.