Model comparison
GPT-4o mini vs Llama-3.3-70B-Instruct
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 25.5 on the Noometry Index.
Last verified . 37 shared benchmarks.
MetaSummary
- They share 37 benchmarks with published results for both. GPT-4o mini scores higher in 3 categories and Llama-3.3-70B-Instruct in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama-3.3-70B-Instruct leads 30.6 to 17.7.
- The biggest single-benchmark swing is LiveBench Instruction Following: 56.8% for GPT-4o mini and 82.7% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.15 / $0.60 for GPT-4o mini.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 25.5 | 30.6 |
| Released | 2024-07-18 | 2024-12-06 |
| Weights | Proprietary | Open |
| Context window | 128K | 128K |
| Max output | 16K | 4K |
| Input $ / M tokens | $0.15 | $0.10 |
| Output $ / M tokens | $0.60 | $0.32 |
| Results tracked | 60 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
GPT-4o mini: 22.0 (#335), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| WeirdML | 11.8% | 14.4% |
| BigCodeBench Instruct | 46.1% | 46.9% |
| LiveBench Coding | 43.1% | 36.6% |
| LMArena Coding | 1290 | 1268 |
| BigCodeBench Complete | 57.4% | 57.5% |
| Aider Polyglot | 3.6% | — |
| SciCode | — | 26% |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use GPT-4o mini leads
GPT-4o mini: 27.5 (#101), Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| BALROG | 17.4% | 23% |
| Berkeley Function Calling Leaderboard | — | 31.9% |
Reasoning Llama-3.3-70B-Instruct leads
GPT-4o mini: 8.7 (#347), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| SimpleBench | 10.7% | 19.9% |
| LiveBench Reasoning | 32.8% | 50.8% |
| LMArena Hard Prompts | 1267 | 1257 |
| DTBench | 54.4% | 59.5% |
| LiveBench Data Analysis | 50% | 49.5% |
| LMCA | 10.4% | 17.5% |
| Epoch Capabilities Index | 126.56 | 127.33 |
| LiveBench | 41.3% | 50.2% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 28.8% | — |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 12% | — |
| ForecastBench | — | 58.6 |
| PIQA | 88.7% | — |
Math Llama-3.3-70B-Instruct leads
GPT-4o mini: 10.4 (#314), Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 5.1% |
| LiveBench Math | 36.3% | 42.2% |
| LMArena Math | 1267 | 1267 |
| MATH Level 5 | 52.6% | 41.6% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | 28% | — |
| GSM8K | 91.3% | — |
Knowledge Llama-3.3-70B-Instruct leads
GPT-4o mini: 17.7 (#284), Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 37.7% | 47.4% |
| Confabulations | 37.2% | 22.8% |
| LMArena Expert | 1235 | 1225 |
| MMLU | 81.8% | 86.3% |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Vectara Hallucination Rate | — | 4.1% |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Llama-3.3-70B-Instruct: —
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual GPT-4o mini leads
GPT-4o mini: 42.0 (#199), Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1266 | 1236 |
| LMArena Chinese | 1265 | 1217 |
| LMArena French | 1297 | 1281 |
| LMArena German | 1272 | 1251 |
| LMArena Japanese | 1216 | 1150 |
| LMArena Korean | 1195 | 1143 |
| LMArena Russian | 1275 | 1252 |
| LMArena Spanish | 1276 | 1270 |
Instruction Following Llama-3.3-70B-Instruct leads
GPT-4o mini: 61.9 (#239), Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Instruction Following | 56.8% | 82.7% |
| LMArena Instruction Following | 1258 | 1242 |
| IFEval | 78.2% | — |
Long Context GPT-4o mini leads
GPT-4o mini: 39.1 (#186), Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1289 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Llama-3.3-70B-Instruct leads
GPT-4o mini: 39.5 (#248), Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | GPT-4o mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1286 | 1274 |
| LMArena Creative Writing | 1268 | 1250 |
| LMArena Multi-Turn | 1285 | 1280 |
| LiveBench Language | 28.6% | 39.2% |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
Frequently asked questions
Is GPT-4o mini better than Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 25.5 on the Noometry Index.
Which is cheaper, GPT-4o mini or Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; GPT-4o mini lists at $0.15 and $0.60.
Is GPT-4o mini or Llama-3.3-70B-Instruct better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do GPT-4o mini and Llama-3.3-70B-Instruct share?
37 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Llama-3.3-70B-Instruct has 43.