Model comparison
Codellama 70b Instruct vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 44.8 to 33.3 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-5.4 mini in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.4 mini leads 64.2 to 33.6.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | GPT-5.4 mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.3 | 44.8 |
| Released | — | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $4.50 |
| Results tracked | 7 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
Codellama 70b Instruct: 37.0 (#189), GPT-5.4 mini: 45.0 (#67)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1438 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, GPT-5.4 mini: 29.6 (#74)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
Codellama 70b Instruct: 19.2 (#241), GPT-5.4 mini: 30.3 (#77)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1424 |
| ARC-AGI-2 | — | 18.9% |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| DTBench | — | 80% |
| LMCA | — | 40.8% |
| Epoch Capabilities Index | — | 148.83 |
| ForecastBench | — | 57 |
Math Not comparable
Codellama 70b Instruct: —, GPT-5.4 mini: 45.4 (#63)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 21% |
| LMArena Math | — | 1418 |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Not comparable
Codellama 70b Instruct: —, GPT-5.4 mini: 51.4 (#62)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | — | 86.9% |
| SimpleQA Verified | — | 29.4% |
| Vectara Hallucination Rate | — | 5.5% |
| LMArena Expert | — | 1434 |
Multimodal Not comparable
Codellama 70b Instruct: —, GPT-5.4 mini: 39.0 (#51)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual GPT-5.4 mini leads
Codellama 70b Instruct: 24.9 (#283), GPT-5.4 mini: 52.1 (#94)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 992 | 1405 |
| LMArena Chinese | — | 1446 |
| LMArena French | — | 1440 |
| LMArena German | — | 1407 |
| LMArena Japanese | — | 1375 |
| LMArena Korean | — | 1369 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1403 |
Instruction Following GPT-5.4 mini leads
Codellama 70b Instruct: 52.1 (#288), GPT-5.4 mini: 74.3 (#99)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1024 | 1405 |
Long Context Not comparable
Codellama 70b Instruct: —, GPT-5.4 mini: 42.9 (#107)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | — | 1407 |
Writing & Preference GPT-5.4 mini leads
Codellama 70b Instruct: 33.6 (#272), GPT-5.4 mini: 64.2 (#56)
| Benchmark | Codellama 70b Instruct | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1057 | 1411 |
| LMArena Creative Writing | — | 1370 |
| EQ-Bench Creative Writing | — | 1665 |
| LMArena Multi-Turn | — | 1429 |
Frequently asked questions
Is Codellama 70b Instruct better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 44.8 to 33.3 on the Noometry Index.
Is Codellama 70b Instruct or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 37.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and GPT-5.4 mini share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-5.4 mini has 46.