Model comparison
GPT-5-Codex vs Granite 3.1 8b Instruct
GPT-5-Codex is the stronger model overall, scoring 37.3 to 31.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 21.2.
- Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5-Codex | Granite 3.1 8b Instruct | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 37.3 | 31.8 |
| Released | 2025-09-15 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 3 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
GPT-5-Codex: 41.9 (#100), Granite 3.1 8b Instruct: 33.9 (#232)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1186 |
Agentic & Tool Use GPT-5-Codex leads
GPT-5-Codex: 30.8 (#66), Granite 3.1 8b Instruct: 23.9 (#113)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning GPT-5-Codex leads
GPT-5-Codex: 30.0 (#80), Granite 3.1 8b Instruct: 21.2 (#204)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LMArena Hard Prompts | — | 1146 |
Math Not comparable
GPT-5-Codex: —, Granite 3.1 8b Instruct: 30.4 (#210)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | — | 1152 |
Knowledge Not comparable
GPT-5-Codex: —, Granite 3.1 8b Instruct: 30.6 (#218)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | — | 1142 |
Multilingual Not comparable
GPT-5-Codex: —, Granite 3.1 8b Instruct: 31.1 (#255)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | — | 1099 |
| LMArena Chinese | — | 1145 |
| LMArena Russian | — | 1092 |
Instruction Following Not comparable
GPT-5-Codex: —, Granite 3.1 8b Instruct: 58.9 (#254)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1131 |
Long Context Not comparable
GPT-5-Codex: —, Granite 3.1 8b Instruct: 35.2 (#236)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1162 |
Writing & Preference Not comparable
GPT-5-Codex: —, Granite 3.1 8b Instruct: 35.7 (#261)
| Benchmark | GPT-5-Codex | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | — | 1150 |
| LMArena Creative Writing | — | 1129 |
| LMArena Multi-Turn | — | 1108 |
Frequently asked questions
Is GPT-5-Codex better than Granite 3.1 8b Instruct?
GPT-5-Codex is the stronger model overall, scoring 37.3 to 31.8 on the Noometry Index.
Is GPT-5-Codex or Granite 3.1 8b Instruct better for coding?
GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 33.9 in the Noometry coding category.
How many benchmarks do GPT-5-Codex and Granite 3.1 8b Instruct share?
0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Granite 3.1 8b Instruct has 13.