Model comparison
GPT-5 vs Granite 3.0 2b Instruct
GPT-5 is the stronger model overall, scoring 50.9 to 30.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GPT-5 scores higher in 8 categories and Granite 3.0 2b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 32.5.
- Granite 3.0 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5 | Granite 3.0 2b Instruct | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 50.9 | 30.2 |
| Released | 2025-08-07 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 69 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
GPT-5: 50.7 (#39), Granite 3.0 2b Instruct: 27.8 (#311)
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Coding | 1436 | 1090 |
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| Aider Polyglot | 88% | — |
| LMArena WebDev | 1417 | — |
| SciCode | 42.9% | — |
| GSO | 6.9% | — |
| WeirdML | 60.7% | — |
| BigCodeBench Instruct | — | 20.5% |
| ALE-Bench | 1,162 | — |
| AlgoTune | 1.67 | — |
Agentic & Tool Use Not comparable
GPT-5: 33.0 (#53), Granite 3.0 2b Instruct: —
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |
Reasoning GPT-5 leads
GPT-5: 38.3 (#55), Granite 3.0 2b Instruct: 19.6 (#234)
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1415 | 1073 |
| ARC-AGI-2 | 9.9% | — |
| SimpleBench | 56.7% | — |
| Kagi LLM Benchmark | 72.7% | — |
| ARC-AGI-1 | 65.7% | — |
| CritPt | 12.6% | — |
| Chess Puzzles | 37% | — |
| EnigmaEval | 10.5% | — |
| EBR-Bench | 12.7% | — |
| Mystery Game Puzzles | 23% | — |
| DTBench | 90.7% | — |
| LMCA | 40% | — |
| Epoch Capabilities Index | 150 | — |
| ForecastBench | 61.4 | — |
Math GPT-5 leads
GPT-5: 54.6 (#36), Granite 3.0 2b Instruct: 29.7 (#215)
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | 1406 | 1117 |
| FrontierMath (Tiers 1-3) | 55.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 91.4% | — |
| ProofBench | 18% | — |
| Omni-MATH | 64.7% | — |
| MATH Level 5 | 98.1% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5 leads
GPT-5: 56.5 (#37), Granite 3.0 2b Instruct: 28.4 (#238)
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | 1420 | 1064 |
| GPQA Diamond | 86.2% | — |
| Humanity's Last Exam | 25.3% | — |
| SimpleQA Verified | 50.1% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |
Multimodal Not comparable
GPT-5: 46.1 (#12), Granite 3.0 2b Instruct: —
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Vision | 1232 | — |
| GeoBench | 81% | — |
| VPCT | 66% | — |
Multilingual GPT-5 leads
GPT-5: 51.5 (#105), Granite 3.0 2b Instruct: 27.1 (#273)
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | 1397 | 1033 |
| LMArena Chinese | 1423 | 1070 |
| LMArena Russian | 1406 | 1045 |
| LMArena French | 1409 | — |
| LMArena German | 1415 | — |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1361 | — |
| LMArena Spanish | 1398 | — |
Instruction Following GPT-5 leads
GPT-5: 74.0 (#107), Granite 3.0 2b Instruct: 54.2 (#279)
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1388 | 1056 |
| IFEval | 87.5% | — |
Long Context GPT-5 leads
GPT-5: 69.5 (#2), Granite 3.0 2b Instruct: 32.5 (#263)
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1399 | 1071 |
| Fiction.LiveBench | 97.2% | — |
Writing & Preference GPT-5 leads
GPT-5: 63.5 (#63), Granite 3.0 2b Instruct: 29.8 (#287)
| Benchmark | GPT-5 | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | 1406 | 1080 |
| LMArena Creative Writing | 1365 | 1046 |
| LMArena Multi-Turn | 1426 | 1053 |
| Short-Story Creative Writing | 86% | — |
| EQ-Bench Creative Writing | 1627 | — |
| WildBench | 85.7% | — |
Frequently asked questions
Is GPT-5 better than Granite 3.0 2b Instruct?
GPT-5 is the stronger model overall, scoring 50.9 to 30.2 on the Noometry Index.
Is GPT-5 or Granite 3.0 2b Instruct better for coding?
GPT-5 scores higher on coding benchmarks: 50.7 versus 27.8 in the Noometry coding category.
How many benchmarks do GPT-5 and Granite 3.0 2b Instruct share?
12 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and Granite 3.0 2b Instruct has 13.