Model comparison
Gemma 4 31B IT vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 43.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Gemma 4 31B IT scores higher in 5 categories and Kimi K2 Thinking Turbo in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 37.9.
- The biggest single-benchmark swing is Chess Puzzles: 5% for Gemma 4 31B IT and 20% for Kimi K2 Thinking Turbo.
Side by side
| Gemma 4 31B IT | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 43.2 | 45.4 |
| Released | 2026-04-02 | 2025-11-06 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 41.9 (#98), Kimi K2 Thinking Turbo: 38.1 (#166)
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena WebDev | 1364 | 1322 |
| LMArena Coding | 1459 | 1454 |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Reasoning Kimi K2 Thinking Turbo leads
Gemma 4 31B IT: 26.4 (#119), Kimi K2 Thinking Turbo: 31.4 (#72)
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 5% | 20% |
| LMArena Hard Prompts | 1448 | 1428 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Kimi K2 Thinking Turbo leads
Gemma 4 31B IT: 41.3 (#72), Kimi K2 Thinking Turbo: 45.5 (#62)
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 83.1% |
| LMArena Math | 1464 | 1429 |
Knowledge Kimi K2 Thinking Turbo leads
Gemma 4 31B IT: 37.9 (#141), Kimi K2 Thinking Turbo: 50.9 (#64)
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 75.8% | 84.2% |
| LMArena Expert | 1465 | 1439 |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.0 (#32), Kimi K2 Thinking Turbo: —
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 54.0 (#52), Kimi K2 Thinking Turbo: 51.6 (#104)
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1431 | 1398 |
| LMArena Chinese | 1478 | 1457 |
| LMArena French | 1436 | 1425 |
| LMArena Russian | 1462 | 1390 |
| LMArena Spanish | 1443 | 1407 |
| LMArena German | — | 1390 |
| LMArena Japanese | — | 1356 |
| LMArena Korean | — | 1329 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.6 (#58), Kimi K2 Thinking Turbo: 74.2 (#103)
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1433 | 1403 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#67), Kimi K2 Thinking Turbo: 43.2 (#99)
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1446 | 1415 |
Writing & Preference Too close to call
Gemma 4 31B IT: 60.7 (#92), Kimi K2 Thinking Turbo: 60.2 (#99)
| Benchmark | Gemma 4 31B IT | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1443 | 1415 |
| LMArena Creative Writing | 1416 | 1373 |
| LMArena Multi-Turn | 1452 | 1414 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 43.2 on the Noometry Index.
Is Gemma 4 31B IT or Kimi K2 Thinking Turbo better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 38.1 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and Kimi K2 Thinking Turbo share?
18 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Kimi K2 Thinking Turbo has 21.