Model comparison
Codellama 70b Instruct vs GPT-5.5 Instant
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and GPT-5.5 Instant in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.5 Instant leads 61.8 to 33.4.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | GPT-5.5 Instant | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.7 | 42.7 |
| Released | — | 2026-05-05 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 Instant leads
Codellama 70b Instruct: 37.6 (#193), GPT-5.5 Instant: 44.3 (#74)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| SciCode | — | 48.6% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1433 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning GPT-5.5 Instant leads
Codellama 70b Instruct: 20.1 (#242), GPT-5.5 Instant: 24.9 (#155)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1426 |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Epoch Capabilities Index | — | 142.52 |
Math Not comparable
Codellama 70b Instruct: —, GPT-5.5 Instant: 26.5 (#259)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 26.3% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 68.1% |
| LMArena Math | — | 1420 |
Knowledge Not comparable
Codellama 70b Instruct: —, GPT-5.5 Instant: 48.9 (#74)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| GPQA Diamond | — | 82.5% |
| LMArena Expert | — | 1409 |
Multimodal Not comparable
Codellama 70b Instruct: —, GPT-5.5 Instant: 40.0 (#52)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| LMArena Vision | — | 1250 |
| LMArena Document | — | 1403 |
Multilingual GPT-5.5 Instant leads
Codellama 70b Instruct: 24.8 (#288), GPT-5.5 Instant: 52.8 (#80)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| LMArena Non-English | 992 | 1417 |
| LMArena Chinese | — | 1456 |
| LMArena French | — | 1428 |
| LMArena German | — | 1411 |
| LMArena Japanese | — | 1408 |
| LMArena Korean | — | 1392 |
| LMArena Russian | — | 1431 |
| LMArena Spanish | — | 1429 |
Instruction Following GPT-5.5 Instant leads
Codellama 70b Instruct: 51.9 (#293), GPT-5.5 Instant: 74.2 (#100)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1024 | 1406 |
Long Context Not comparable
Codellama 70b Instruct: —, GPT-5.5 Instant: 43.4 (#96)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| LMArena Longer Query | — | 1422 |
Writing & Preference GPT-5.5 Instant leads
Codellama 70b Instruct: 33.4 (#277), GPT-5.5 Instant: 61.8 (#85)
| Benchmark | Codellama 70b Instruct | GPT-5.5 Instant |
|---|---|---|
| LMArena Text | 1057 | 1419 |
| LMArena Creative Writing | — | 1419 |
| LMArena Multi-Turn | — | 1433 |
Frequently asked questions
Is Codellama 70b Instruct better than GPT-5.5 Instant?
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or GPT-5.5 Instant better for coding?
GPT-5.5 Instant scores higher on coding benchmarks: 44.3 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and GPT-5.5 Instant share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-5.5 Instant has 27.