ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemma 4 31BvsGLM-4.7-Flash

Gemma 4 31B leads 2 of 2 shared benchmarks. Gemma 4 31B has the larger context window (256K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
2 – 0
Gemma 4 31B leads
Cheaper per token
list price, input + output
Larger context
Gemma 4 31B
256K tokens
Provider uptime (30d)
100% · —
Google · Z.ai
Gemma 4 31B
Google · released 2026-04-02
textvision
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
6 · 5 core
text
Context
200K
Max out
131K
Input /1M
$0
Output /1M
$0
Cached /1M
$0
Scores
3 · 3 core
Quality

Benchmark matrix

BenchmarkGemma 4 31BGLM-4.7-FlashΔEdge
Reported by both · 2
GPQA Diamond84.3% 60.5% epoch+23.8 ptGemma 4 31B
LMArena Elo1441.7 1352.2 +89.5Gemma 4 31B
Only Gemma 4 31B reports · 4
MMLU-Pro85.2% not reported
AIME 202689.2% not reported
Humanity's Last Exam (no tools)19.5% not reported
LiveCodeBench v680% not reported
Only GLM-4.7-Flash reports · 1
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported58.3% epoch
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Gemma 4 31B minus GLM-4.7-Flash in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGemma 4 31BGLM-4.7-FlashEdge
Context window256K tokens200K tokensGemma 4 31B
Max output131K tokens
Input price / 1M$0
Output price / 1M$0
Cached input / 1M$0
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0
Modalitiestext · visiontextGemma 4 31B
Released2026-04-02
Cited benchmark scores63
Reliability

Provider status

All providers
More matchups

GLM-4.7-Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Gemma 4 31B and GLM-4.7-Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.