Gemma 4 31B IT
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
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
29
estimated
Long-horizon autonomy
38
estimated
Knowledge-work agents
24
estimated
Computer use
18
estimated
Security & context learning
30
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 64 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 30 | |
| DeepSWE | est. | 6% | predicted 22 | |
| FrontierSWE | est. | 5% | predicted 3 | |
| CursorBench | est. | 4% | predicted 25 | |
| GSO-Bench | est. | 4% | predicted 7 | |
| METR Time Horizons | est. | 10% | predicted 63 | |
| Vending-Bench 2 | est. | 6% | predicted 11 | |
| PostTrainBench | est. | 4% | predicted 16 | |
| APEX-Agents | est. | 8% | predicted 22 | |
| GDPval | est. | 7% | predicted 28 | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 44 | |
| OSWorld 2.0 | est. | 6% | predicted 2 | |
| OSWorld | est. | 4% | predicted 41 | |
| Cybench | est. | 5% | predicted 44 | |
| CL-bench | est. | 5% | predicted 16 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| CritPt | Reasoning | 1.4% | source |
| DTBench | Knowledge | 82.7% | source |
| GPQA Diamond | Reasoning | 75.8% | source |
| LMCA | Knowledge | 39.3% | source |
| OTIS Mock AIME | Math | 73.3% | source |
| SciCode | Coding | 45.5% | source |
| SimpleQA Verified | Knowledge | 10.4% | source |
| WebDev Arena | Coding | 1364 | source |
API hosts
Live prices and uptime for every host serving Gemma 4 31B IT via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Chutes | $0.12 | $0.37 | $0.012 | $0.040 | 99.9% | fp4 |
| NextBit | $0.13 | $0.34 | $0.075 | $0.090 | 99.9% | fp4 |
| Parasail | $0.15 | $0.40 | $0.060 | $0.090 | 99.2% | fp8 |
| DeepInfra | $0.14 | $0.51 | $0.075 | $0.10 | 100.0% | fp4 |
| PrimeIntellect | $0.15 | $0.25 | $0.076 | $0.10 | 98.5% | fp8 |
| CoreWeave | $0.10 | $0.34 | $0.10 | $0.11 | 100.0% | fp4 |
| KT | $0.10 | $0.34 | $0.10 | $0.11 | 100.0% | — |
| Venice | $0.12 | $0.36 | $0.090 | $0.11 | 100.0% | fp4 |
| Modal | $0.34 | $0.10 | $0.10 | $0.13 | 100.0% | — |
| Crusoe | $0.14 | $0.40 | $0.14 | $0.15 | 100.0% | bf16 |
| Friendli | $0.14 | $0.40 | — | $0.15 | 100.0% | — |
| Novita | $0.14 | $0.40 | — | $0.15 | 99.8% | bf16 |
| DeepInfra | $0.16 | $0.32 | — | $0.17 | 98.9% | fp8 |
| DeepInfra | $0.20 | $0.40 | — | $0.21 | 100.0% | fp8 |
| DeepInfra | $0.30 | $0.60 | — | $0.31 | 99.3% | fp8 |
| ModelRun | $0.75 | $1.00 | $0.20 | $0.32 | 100.0% | fp4 |
| SiliconFlow | $0.75 | $1.00 | $0.25 | $0.36 | 100.0% | fp8 |
| SambaNova | $0.38 | $1.15 | — | $0.42 | 93.6% | — |