Model comparison
GPT-5 Nano vs Granite 3.1 8b Instruct
GPT-5 Nano is the stronger model overall, scoring 33.5 to 32.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. GPT-5 Nano scores higher in 5 categories and Granite 3.1 8b Instruct in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5 Nano leads 75.0 to 58.6.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 51.5% for GPT-5 Nano and 27.1% for Granite 3.1 8b Instruct.
- Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Granite 3.1 8b Instruct | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 33.5 | 32.4 |
| Released | 2025-08-07 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 49 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Nano: 33.6 (#254), Granite 3.1 8b Instruct: 34.5 (#233)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Coding | 1351 | 1186 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use GPT-5 Nano leads
GPT-5 Nano: 25.8 (#106), Granite 3.1 8b Instruct: 24.1 (#120)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 51.5% | 27.1% |
| Terminal-Bench | 21.8% | — |
Reasoning Granite 3.1 8b Instruct leads
GPT-5 Nano: 16.3 (#306), Granite 3.1 8b Instruct: 22.1 (#207)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1145 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
Math Granite 3.1 8b Instruct leads
GPT-5 Nano: 29.4 (#241), Granite 3.1 8b Instruct: 33.0 (#209)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | 1317 | 1152 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), Granite 3.1 8b Instruct: 31.1 (#220)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | 1321 | 1142 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Granite 3.1 8b Instruct: —
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.3 (#172), Granite 3.1 8b Instruct: 30.9 (#260)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | 1313 | 1099 |
| LMArena Chinese | 1356 | 1145 |
| LMArena Russian | 1296 | 1092 |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Spanish | 1360 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Granite 3.1 8b Instruct: 58.6 (#259)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 1306 | 1131 |
| IFEval | 93.2% | — |
Long Context Granite 3.1 8b Instruct leads
GPT-5 Nano: 31.3 (#281), Granite 3.1 8b Instruct: 35.2 (#241)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | 1312 | 1162 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5 Nano leads
GPT-5 Nano: 39.1 (#249), Granite 3.1 8b Instruct: 35.5 (#266)
| Benchmark | GPT-5 Nano | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | 1320 | 1150 |
| LMArena Creative Writing | 1249 | 1129 |
| LMArena Multi-Turn | 1311 | 1108 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Granite 3.1 8b Instruct?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 32.4 on the Noometry Index.
Is GPT-5 Nano or Granite 3.1 8b Instruct better for coding?
They score almost the same on coding (33.6 vs 34.5); test both on your own repository before choosing.
How many benchmarks do GPT-5 Nano and Granite 3.1 8b Instruct share?
13 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Granite 3.1 8b Instruct has 13.