Model comparison
GPT-3.5-turbo vs Olmo 3.1 32b Instruct
Olmo 3.1 32b Instruct is the stronger model overall, scoring 39.4 to 23.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 16 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Olmo 3.1 32b Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3.1 32b Instruct leads 36.3 to 6.3.
- Olmo 3.1 32b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | Olmo 3.1 32b Instruct | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 23.2 | 39.4 |
| Released | 2023-03-01 | — |
| Weights | Proprietary | Open |
| Context window | 16K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 44 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3.1 32b Instruct leads
GPT-3.5-turbo: 23.9 (#331), Olmo 3.1 32b Instruct: 39.5 (#157)
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Coding | 1136 | 1347 |
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Olmo 3.1 32b Instruct: —
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Olmo 3.1 32b Instruct leads
GPT-3.5-turbo: 13.8 (#332), Olmo 3.1 32b Instruct: 26.4 (#132)
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1322 |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.55 | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Olmo 3.1 32b Instruct leads
GPT-3.5-turbo: 6.3 (#327), Olmo 3.1 32b Instruct: 36.3 (#167)
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Math | 1142 | 1305 |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Olmo 3.1 32b Instruct leads
GPT-3.5-turbo: 10.0 (#303), Olmo 3.1 32b Instruct: 36.1 (#175)
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Expert | 1070 | 1308 |
| GPQA Diamond | 28% | — |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multilingual Olmo 3.1 32b Instruct leads
GPT-3.5-turbo: 31.5 (#258), Olmo 3.1 32b Instruct: 42.6 (#191)
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | 1108 | 1275 |
| LMArena Chinese | 1075 | 1304 |
| LMArena French | 1118 | 1328 |
| LMArena German | 1090 | 1282 |
| LMArena Korean | 1019 | 1206 |
| LMArena Russian | 1123 | 1268 |
| LMArena Spanish | 1121 | 1336 |
| LMArena Japanese | 1043 | — |
Instruction Following Olmo 3.1 32b Instruct leads
GPT-3.5-turbo: 57.9 (#262), Olmo 3.1 32b Instruct: 68.6 (#187)
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1119 | 1299 |
Long Context Olmo 3.1 32b Instruct leads
GPT-3.5-turbo: 34.0 (#254), Olmo 3.1 32b Instruct: 39.9 (#166)
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1121 | 1312 |
Writing & Preference Olmo 3.1 32b Instruct leads
GPT-3.5-turbo: 25.3 (#305), Olmo 3.1 32b Instruct: 50.2 (#185)
| Benchmark | GPT-3.5-turbo | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | 1125 | 1311 |
| LMArena Creative Writing | 1092 | 1264 |
| LMArena Multi-Turn | 1117 | 1309 |
| EQ-Bench Creative Writing | 451 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Olmo 3.1 32b Instruct?
Olmo 3.1 32b Instruct is the stronger model overall, scoring 39.4 to 23.2 on the Noometry Index.
Is GPT-3.5-turbo or Olmo 3.1 32b Instruct better for coding?
Olmo 3.1 32b Instruct scores higher on coding benchmarks: 39.5 versus 23.9 in the Noometry coding category.
How many benchmarks do GPT-3.5-turbo and Olmo 3.1 32b Instruct share?
16 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Olmo 3.1 32b Instruct has 16.