Model comparison
GPT-5.2 Codex vs Granite 3.1 8b Instruct
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 32.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 41.0 to 24.1.
- Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Codex | Granite 3.1 8b Instruct | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 42.6 | 32.4 |
| Released | 2025-12-18 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 5 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 Codex leads
GPT-5.2 Codex: 45.5 (#71), Granite 3.1 8b Instruct: 34.5 (#233)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1186 |
| ALE-Bench | 1,300 | — |
Agentic & Tool Use GPT-5.2 Codex leads
GPT-5.2 Codex: 41.0 (#22), Granite 3.1 8b Instruct: 24.1 (#120)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| Terminal-Bench | 66.5% | — |
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Not comparable
GPT-5.2 Codex: —, Granite 3.1 8b Instruct: 22.1 (#207)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 1145 |
Math Not comparable
GPT-5.2 Codex: —, Granite 3.1 8b Instruct: 33.0 (#209)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | — | 1152 |
Knowledge Not comparable
GPT-5.2 Codex: —, Granite 3.1 8b Instruct: 31.1 (#220)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | — | 1142 |
Multilingual Not comparable
GPT-5.2 Codex: —, Granite 3.1 8b Instruct: 30.9 (#260)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | — | 1099 |
| LMArena Chinese | — | 1145 |
| LMArena Russian | — | 1092 |
Instruction Following Not comparable
GPT-5.2 Codex: —, Granite 3.1 8b Instruct: 58.6 (#259)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1131 |
Long Context Not comparable
GPT-5.2 Codex: —, Granite 3.1 8b Instruct: 35.2 (#241)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1162 |
Writing & Preference Not comparable
GPT-5.2 Codex: —, Granite 3.1 8b Instruct: 35.5 (#266)
| Benchmark | GPT-5.2 Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | — | 1150 |
| LMArena Creative Writing | — | 1129 |
| LMArena Multi-Turn | — | 1108 |
Frequently asked questions
Is GPT-5.2 Codex better than Granite 3.1 8b Instruct?
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 32.4 on the Noometry Index.
Is GPT-5.2 Codex or Granite 3.1 8b Instruct better for coding?
GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 34.5 in the Noometry coding category.
How many benchmarks do GPT-5.2 Codex and Granite 3.1 8b Instruct share?
0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Granite 3.1 8b Instruct has 13.