Gemma 4 26B A4B vs Gemma 4 31B: Release Comparison
Comparison of the Gemma 4 26B A4B and Gemma 4 31B releases: 2 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 4 models.
- For intelligence, Gemma 4 26B A4B scores highest: Gemma 4 26B A4B (Reasoning) at 17, against Gemma 4 31B (Reasoning) at 15 for Gemma 4 31B.
- For output speed, Gemma 4 26B A4B is fastest: Gemma 4 26B A4B (Non-reasoning) at 64 t/s, against Gemma 4 31B (Non-reasoning) at 45 t/s for Gemma 4 31B.
Releases compared
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indices
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better
Further details
Input modality | Output modality | Weights | Provider Benchmarks | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B (Reasoning) |  Google | 17 | - | - | - | - | - | - | - | $0.1 | $0.115 | $0.37 | $0.085 | - | - | - | - | - | - | - | - | - | 25.2B 3.8B active at inference time | 256k | Apr 2026 | - | Yes | Supports: text, image, and video | Supports: text |   +4 | |||
| Gemma 4 31B (Reasoning) | Google | 15 | 15 | 11 | 15 | - | 17 | 22 | $0.00 | $0.0 | $0.00 | $0.00 | - | $0 | 13k | 8k | 49M | 35 | 1.01s | 50.72s | 65.04s | 345.28s | 30.7B | 256k | Apr 2026 | - | Yes | Supports: text, image, and video | Supports: text |    +11 | |||
| Gemma 4 31B (Non-reasoning) | Google | 14 | - | - | - | - | - | - | - | $0.2 | $0.14 | $0.40 | $0.14 | - | - | - | - | 45 | 1.95s | 1.95s | 13.17s | - | 30.7B | 256k | Apr 2026 | - | No | Supports: text, image, and video | Supports: text |   +8 | |||
| Gemma 4 26B A4B (Non-reasoning) | Google | 13 | - | - | - | - | - | - | - | $0.2 | $0.13 | $0.40 | $0.125 | - | - | - | - | 64 | 1.46s | 1.46s | 9.22s | - | 25.2B 3.8B active at inference time | 256k | Apr 2026 | - | No | Supports: text, image, and video | Supports: text | +4 | |||