Model comparison
Gemma 3 27B vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 30.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 25.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 22.5% for Gemma 3 27B and 83.1% for Kimi K2 Thinking Turbo.
Side by side
| Gemma 3 27B | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 30.5 | 45.4 |
| Released | 2025-03-11 | 2025-11-06 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.16 | — |
| Results tracked | 43 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
Gemma 3 27B: 22.1 (#329), Kimi K2 Thinking Turbo: 38.1 (#166)
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1322 | 1454 |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1322 |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 24.9 (#105), Kimi K2 Thinking Turbo: —
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Kimi K2 Thinking Turbo leads
Gemma 3 27B: 16.3 (#297), Kimi K2 Thinking Turbo: 31.4 (#72)
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 0% | 20% |
| LMArena Hard Prompts | 1340 | 1428 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Kimi K2 Thinking Turbo leads
Gemma 3 27B: 24.4 (#261), Kimi K2 Thinking Turbo: 45.5 (#62)
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 83.1% |
| LMArena Math | 1312 | 1429 |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Kimi K2 Thinking Turbo leads
Gemma 3 27B: 25.4 (#256), Kimi K2 Thinking Turbo: 50.9 (#64)
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 47.7% | 84.2% |
| LMArena Expert | 1303 | 1439 |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.0 (#94), Kimi K2 Thinking Turbo: —
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Vision | 1165 | — |
| GeoBench | 52% | — |
Multilingual Kimi K2 Thinking Turbo leads
Gemma 3 27B: 47.0 (#150), Kimi K2 Thinking Turbo: 51.6 (#104)
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1334 | 1398 |
| LMArena Chinese | 1347 | 1457 |
| LMArena French | 1368 | 1425 |
| LMArena German | 1362 | 1390 |
| LMArena Japanese | 1287 | 1356 |
| LMArena Korean | 1308 | 1329 |
| LMArena Russian | 1349 | 1390 |
| LMArena Spanish | 1348 | 1407 |
Instruction Following Kimi K2 Thinking Turbo leads
Gemma 3 27B: 70.8 (#155), Kimi K2 Thinking Turbo: 74.2 (#103)
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1321 | 1403 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Kimi K2 Thinking Turbo leads
Gemma 3 27B: 27.6 (#288), Kimi K2 Thinking Turbo: 43.2 (#99)
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1333 | 1415 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Kimi K2 Thinking Turbo leads
Gemma 3 27B: 52.7 (#161), Kimi K2 Thinking Turbo: 60.2 (#99)
| Benchmark | Gemma 3 27B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1358 | 1415 |
| LMArena Creative Writing | 1346 | 1373 |
| LMArena Multi-Turn | 1344 | 1414 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 30.5 on the Noometry Index.
Is Gemma 3 27B or Kimi K2 Thinking Turbo better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 22.1 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Kimi K2 Thinking Turbo share?
20 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Kimi K2 Thinking Turbo has 21.