Model comparison
Codellama 70b Instruct vs Olmo 3.1 32b Think
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Olmo 3.1 32b Think in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Olmo 3.1 32b Think leads 65.6 to 51.9.
Side by side
| Codellama 70b Instruct | Olmo 3.1 32b Think | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 33.7 | 37.9 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 70b Instruct: 37.6 (#193), Olmo 3.1 32b Think: 37.7 (#189)
| Benchmark | Codellama 70b Instruct | Olmo 3.1 32b Think |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1291 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Olmo 3.1 32b Think leads
Codellama 70b Instruct: 20.1 (#242), Olmo 3.1 32b Think: 25.2 (#150)
| Benchmark | Codellama 70b Instruct | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1272 |
Math Not comparable
Codellama 70b Instruct: —, Olmo 3.1 32b Think: 36.3 (#168)
| Benchmark | Codellama 70b Instruct | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Math | — | 1305 |
Knowledge Not comparable
Codellama 70b Instruct: —, Olmo 3.1 32b Think: 35.7 (#181)
| Benchmark | Codellama 70b Instruct | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Expert | — | 1295 |
Multilingual Olmo 3.1 32b Think leads
Codellama 70b Instruct: 24.8 (#288), Olmo 3.1 32b Think: 38.1 (#231)
| Benchmark | Codellama 70b Instruct | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Non-English | 992 | 1209 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1260 |
| LMArena German | — | 1262 |
| LMArena Russian | — | 1193 |
| LMArena Spanish | — | 1289 |
Instruction Following Olmo 3.1 32b Think leads
Codellama 70b Instruct: 51.9 (#293), Olmo 3.1 32b Think: 65.6 (#218)
| Benchmark | Codellama 70b Instruct | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Instruction Following | 1024 | 1247 |
Long Context Not comparable
Codellama 70b Instruct: —, Olmo 3.1 32b Think: 38.6 (#195)
| Benchmark | Codellama 70b Instruct | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Longer Query | — | 1272 |
Writing & Preference Olmo 3.1 32b Think leads
Codellama 70b Instruct: 33.4 (#277), Olmo 3.1 32b Think: 46.2 (#220)
| Benchmark | Codellama 70b Instruct | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Text | 1057 | 1272 |
| LMArena Creative Writing | — | 1226 |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is Codellama 70b Instruct better than Olmo 3.1 32b Think?
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Olmo 3.1 32b Think better for coding?
They score almost the same on coding (37.6 vs 37.7); test both on your own repository before choosing.
How many benchmarks do Codellama 70b Instruct and Olmo 3.1 32b Think share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Olmo 3.1 32b Think has 15.