Llama 4 Maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward…
Shogo Agent Index
UnrankedNot ranked yet: 0 agentic benchmarks measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
15
estimated
Long-horizon autonomy
25
estimated
Knowledge-work agents
15
estimated
Computer use
5
estimated
Security & context learning
13
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 46 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 6 | |
| DeepSWE | est. | 6% | predicted 7 | |
| FrontierSWE | est. | 5% | predicted 1 | |
| CursorBench | est. | 4% | predicted 15 | |
| GSO-Bench | est. | 4% | predicted 1 | |
| METR Time Horizons | est. | 10% | predicted 46 | |
| Vending-Bench 2 | est. | 6% | predicted 1 | |
| PostTrainBench | est. | 4% | predicted 10 | |
| APEX-Agents | est. | 8% | predicted 8 | |
| GDPval | est. | 7% | predicted 14 | |
| Remote Labor Index | est. | 5% | predicted 0 | |
| DeepResearch Bench | est. | 5% | predicted 40 | |
| OSWorld 2.0 | est. | 6% | predicted 0 | |
| OSWorld | est. | 4% | predicted 11 | |
| Cybench | est. | 5% | predicted 15 | |
| CL-bench | est. | 5% | predicted 12 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Aider Polyglot | Coding | 15.6% | source |
| ARC-AGI | Reasoning | 4.4% | source |
| ARC-AGI-2 | Reasoning | 0.0% | source |
| CritPt | Reasoning | 0.0% | source |
| DTBench | Knowledge | 61.9% | source |
| Fiction.LiveBench | Long context | 46.2% | source |
| GeoBench | Multimodal | 52.0% | source |
| GPQA Diamond | Reasoning | 67.0% | source |
| Humanity's Last Exam | Reasoning | 5.7% | source |
| LMCA | Knowledge | 15.9% | source |
| MATH Level 5 | Math | 73.0% | source |
| OTIS Mock AIME | Math | 20.6% | source |
| SciCode | Coding | 31.7% | source |
| SimpleBench | Reasoning | 27.7% | source |
API hosts
Live prices and uptime for every host serving Llama 4 Maverick via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Parasail | $0.35 | $1.00 | $0.17 | $0.24 | 100.0% | fp8 |