Model comparison
Gemma 3 4B vs OLMo 2 Furious 13B
OLMo 2 Furious 13B is the stronger model overall, scoring 29.2 to 27.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- The widest gap is in coding, where Gemma 3 4B leads 35.3 to 28.1.
Side by side
| Gemma 3 4B | OLMo 2 Furious 13B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 27.9 | 29.2 |
| Released | 2025-03-12 | 2024-12-31 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.3 (#214), OLMo 2 Furious 13B: 28.1 (#309)
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| LiveBench Coding | — | 10.4% |
| LMArena Coding | 1230 | — |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.7 (#134), OLMo 2 Furious 13B: —
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning OLMo 2 Furious 13B leads
Gemma 3 4B: 12.7 (#330), OLMo 2 Furious 13B: 14.8 (#312)
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 16.3% |
| LMArena Hard Prompts | 1253 | — |
| DTBench | 50.9% | — |
| LiveBench Data Analysis | — | 20.6% |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
| LiveBench | — | 22.1% |
Math OLMo 2 Furious 13B leads
Gemma 3 4B: 15.8 (#286), OLMo 2 Furious 13B: 21.3 (#270)
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| Omni-MATH | — | 15.6% |
| LiveBench Math | — | 13.6% |
| LMArena Math | 1239 | — |
Knowledge OLMo 2 Furious 13B leads
Gemma 3 4B: 11.8 (#294), OLMo 2 Furious 13B: 18.0 (#278)
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| MMLU-Pro | — | 31% |
| Vectara Hallucination Rate | 6.4% | — |
| GPQA (HELM) | — | 31.6% |
| LMArena Expert | 1223 | — |
Multilingual Not comparable
Gemma 3 4B: 42.7 (#189), OLMo 2 Furious 13B: —
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Gemma 3 4B leads
Gemma 3 4B: 65.4 (#219), OLMo 2 Furious 13B: 61.1 (#243)
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| LiveBench Instruction Following | — | 60.6% |
| IFEval | — | 73% |
| LMArena Instruction Following | 1239 | — |
Long Context Not comparable
Gemma 3 4B: 38.6 (#189), OLMo 2 Furious 13B: —
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| LMArena Longer Query | 1274 | — |
Writing & Preference Too close to call
Gemma 3 4B: 42.2 (#234), OLMo 2 Furious 13B: 43.0 (#226)
| Benchmark | Gemma 3 4B | OLMo 2 Furious 13B |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1270 | — |
| EQ-Bench Creative Writing | 1068 | — |
| WildBench | — | 68.9% |
| LMArena Multi-Turn | 1255 | — |
| LiveBench Language | — | 11.2% |
Frequently asked questions
Is Gemma 3 4B better than OLMo 2 Furious 13B?
OLMo 2 Furious 13B is the stronger model overall, scoring 29.2 to 27.9 on the Noometry Index.
Is Gemma 3 4B or OLMo 2 Furious 13B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.3 versus 28.1 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and OLMo 2 Furious 13B share?
0 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and OLMo 2 Furious 13B has 12.