Model comparison
GPT-5.1-Codex vs Granite 3.1 2b Instruct
GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 33.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in coding, where GPT-5.1-Codex leads 41.9 to 33.4.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1-Codex | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 38.6 | 33.2 |
| Released | 2025-11-12 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 6 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1-Codex leads
GPT-5.1-Codex: 41.9 (#116), Granite 3.1 2b Instruct: 33.4 (#257)
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1337 | — |
| LMArena Coding | — | 1149 |
| ALE-Bench | 1,245 | — |
Agentic & Tool Use Not comparable
GPT-5.1-Codex: 38.0 (#33), Granite 3.1 2b Instruct: —
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| Terminal-Bench | 60.4% | — |
| METR Time Horizons | 70.8% | — |
Reasoning Not comparable
GPT-5.1-Codex: —, Granite 3.1 2b Instruct: 22.0 (#209)
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 1138 |
Math Granite 3.1 2b Instruct leads
GPT-5.1-Codex: 30.3 (#235), Granite 3.1 2b Instruct: 33.1 (#206)
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| ProofBench | 9% | — |
| LMArena Math | — | 1159 |
Knowledge Not comparable
GPT-5.1-Codex: —, Granite 3.1 2b Instruct: 30.8 (#224)
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | — | 1131 |
Multilingual Not comparable
GPT-5.1-Codex: —, Granite 3.1 2b Instruct: 29.1 (#269)
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | — | 1068 |
| LMArena Chinese | — | 1139 |
| LMArena Russian | — | 1063 |
Instruction Following Not comparable
GPT-5.1-Codex: —, Granite 3.1 2b Instruct: 57.7 (#264)
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1116 |
Long Context Not comparable
GPT-5.1-Codex: —, Granite 3.1 2b Instruct: 35.0 (#244)
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1155 |
Writing & Preference Not comparable
GPT-5.1-Codex: —, Granite 3.1 2b Instruct: 34.1 (#274)
| Benchmark | GPT-5.1-Codex | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | — | 1127 |
| LMArena Creative Writing | — | 1116 |
| LMArena Multi-Turn | — | 1099 |
Frequently asked questions
Is GPT-5.1-Codex better than Granite 3.1 2b Instruct?
GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 33.2 on the Noometry Index.
Is GPT-5.1-Codex or Granite 3.1 2b Instruct better for coding?
GPT-5.1-Codex scores higher on coding benchmarks: 41.9 versus 33.4 in the Noometry coding category.
How many benchmarks do GPT-5.1-Codex and Granite 3.1 2b Instruct share?
0 benchmarks have published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and Granite 3.1 2b Instruct has 12.