Model comparison
GPT-4 vs OLMo 2 Furious 13B
GPT-4 and OLMo 2 Furious 13B score almost the same on the Noometry Index (29.1 vs 29.7), so choose on price, context window or the category you care about most.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where OLMo 2 Furious 13B leads 23.1 to 10.8.
- OLMo 2 Furious 13B has downloadable open weights; the other is API-only.
Side by side
| GPT-4 | OLMo 2 Furious 13B | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 29.1 | 29.7 |
| Released | 2023-03-14 | 2024-12-31 |
| Weights | Proprietary | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 38 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 leads
GPT-4: 31.6 (#283), OLMo 2 Furious 13B: 28.6 (#313)
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| LiveBench Coding | — | 10.4% |
| LMArena Coding | 1254 | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, OLMo 2 Furious 13B: —
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning GPT-4 leads
GPT-4: 17.8 (#289), OLMo 2 Furious 13B: 15.5 (#314)
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| Chess Puzzles | 4% | — |
| LiveBench Reasoning | — | 16.3% |
| LMArena Hard Prompts | 1241 | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LiveBench Data Analysis | — | 20.6% |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| LiveBench | — | 22.1% |
| WinoGrande | 87.5% | — |
Math OLMo 2 Furious 13B leads
GPT-4: 10.8 (#309), OLMo 2 Furious 13B: 23.1 (#273)
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| Omni-MATH | — | 15.6% |
| LiveBench Math | — | 13.6% |
| LMArena Math | 1269 | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Too close to call
GPT-4: 18.4 (#282), OLMo 2 Furious 13B: 18.3 (#283)
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| GPQA Diamond | 35.7% | — |
| MMLU-Pro | — | 31% |
| GPQA (HELM) | — | 31.6% |
| LMArena Expert | 1211 | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Not comparable
GPT-4: 40.6 (#215), OLMo 2 Furious 13B: —
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| LMArena Non-English | 1246 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1283 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1251 | — |
| LMArena Spanish | 1261 | — |
Instruction Following GPT-4 leads
GPT-4: 65.3 (#222), OLMo 2 Furious 13B: 60.9 (#248)
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| LiveBench Instruction Following | — | 60.6% |
| IFEval | — | 73% |
| LMArena Instruction Following | 1241 | — |
Long Context Not comparable
GPT-4: 37.7 (#212), OLMo 2 Furious 13B: —
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| LMArena Longer Query | 1244 | — |
Writing & Preference OLMo 2 Furious 13B leads
GPT-4: 34.9 (#268), OLMo 2 Furious 13B: 42.9 (#230)
| Benchmark | GPT-4 | OLMo 2 Furious 13B |
|---|---|---|
| LMArena Text | 1263 | — |
| LMArena Creative Writing | 1244 | — |
| EQ-Bench Creative Writing | 752 | — |
| WildBench | — | 68.9% |
| LMArena Multi-Turn | 1257 | — |
| LiveBench Language | — | 11.2% |
Frequently asked questions
Is GPT-4 better than OLMo 2 Furious 13B?
GPT-4 and OLMo 2 Furious 13B score almost the same on the Noometry Index (29.1 vs 29.7), so choose on price, context window or the category you care about most.
Is GPT-4 or OLMo 2 Furious 13B better for coding?
GPT-4 scores higher on coding benchmarks: 31.6 versus 28.6 in the Noometry coding category.
How many benchmarks do GPT-4 and OLMo 2 Furious 13B share?
0 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and OLMo 2 Furious 13B has 12.