MMODELYST
Models/Gemma 4 31B
MDL

Gemma 4 31B

Google

Verified against Artificial Analysis · Jul 13, 2026
Capability
83
percentile index
Price /M
$0 / $0
in / out
Context
Avg score
55.1
7 benchmarks
AA Intelligence
29.4
index
Speed
35 tok/s
TTFT 0.9s
Released
Apr 2, 2026
About

Gemma 4 31B is a open-weights model in the Gemma family from Google. Benchmarked on 7 evals, averaging 55.1.

Benchmark scores · 7
avg 55.1 — higher is better
GPQA Diamond
85.7
IFBench
75.6
AA Long-Context Reasoning
62
τ²-bench
59.9
SciCode
43.4
Terminal-Bench Hard
36.4
Humanity's Last Exam
22.7
Details
PublisherGoogle
FamilyGemma
Parameters
License
WeightsOpen
ReleasedApr 2, 2026
Performance & price
Output speed35 tok/s
Latency (TTFT)0.9s
First answer50s
Price in / out$0 / $0 per 1M
Coding index43.4

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0/M