← All benchmarks
LiveCodeBench (10/2024-02/2025)
Recent competitive-programming problems, refreshed over time to limit training-data contamination.
Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
- ModelScoreYour cost / mo
- 1Llama 4 Maverick · Metabest value43.4%
- 2Llama 4 Scout · Metabest value32.8%
“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.
How each maker reported it
- Llama 4 Maverick Benchmarks: Instruction tuned models
Meta's own 0-shot results on bf16 weights. Llama 3.x models have no image support and a 128K context, so those cells are not reported.
- Llama 4 Scout Benchmarks: Instruction tuned models
Meta's own 0-shot results on bf16 weights. Llama 3.x models have no image support and a 128K context, so those cells are not reported.
Only each model's own maker's number is shown; scores a maker reports for rival models are left out.