Compare / head-to-head
Gemma 4 31BvsGPT-5.5
GPT-5.5 leads 3 of 3 shared benchmarks. GPT-5.5 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 3
GPT-5.5 leads
Cheaper per token
—
list price, input + output
Larger context
GPT-5.5
1M tokens
Provider uptime (30d)
100% · 94.2446%
Google · OpenAI
Gemma 4 31B
Google · released 2026-04-02
textvision
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 5 core
Quality
Benchmark matrix
3 shared · 3 only Gemma 4 31B · 18 only GPT-5.5| Benchmark | Gemma 4 31B | GPT-5.5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| GPQA Diamond | 84.3% ↗ | 90.7% ↗epoch | -6.4 pt | GPT-5.5 |
| AIME 2026 | 89.2% ↗ | 100% ↗matharena ⚠ | -10.8 pt | GPT-5.5 |
| LMArena Elo | 1441.7 ↗ | 1465.6 ↗ | -23.9 | GPT-5.5 |
| Only Gemma 4 31B reports · 3 | ||||
| MMLU-Pro | 85.2% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 19.5% ↗ | not reported | — | — |
| LiveCodeBench v6 | 80% ↗ | not reported | — | — |
| Only GPT-5.5 reports · 18 | ||||
| ARC-AGI-1 (Verified) | not reported | 95% ↗ | — | — |
| ARC-AGI-2 (Verified) | not reported | 85% ↗ | — | — |
| BrowseComp | not reported | 84.4% ↗ | — | — |
| FrontierMath Tier 1-3 | not reported | 51.7% ↗ | — | — |
| FrontierMath Tier 4 | not reported | 35.4% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 72.5% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 85.3% ↗epoch | — | — |
| GDPval (wins or ties) | not reported | 84.9% ↗ | — | — |
| MCP Atlas | not reported | 75.3% ↗ | — | — |
| MMMU-Pro (no tools) | not reported | 81.2% ↗ | — | — |
| MMMU-Pro (with tools) | not reported | 83.2% ↗ | — | — |
| OSWorld-Verified | not reported | 78.7% ↗ | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 84.4% ↗epoch | — | — |
| SimpleQA Verified | not reported | 63% ↗epoch | — | — |
| SWE-Bench Pro | not reported | 58.6% ↗ | — | — |
| Tau2-bench Telecom | not reported | 98% ↗ | — | — |
| Terminal-Bench 2.0 | not reported | 82.7% ↗ | — | — |
| Toolathlon | not reported | 55.6% ↗ | — | — |
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 GPT-5.5 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
Official pricing pages and model cards| Spec | Gemma 4 31B | GPT-5.5 | Edge |
|---|---|---|---|
| Context window | 256K tokens | 1M tokens | GPT-5.5 |
| Max output | — | 128K tokens | — |
| Input price / 1M | — | $5 ↗ | — |
| Output price / 1M | — | $30 ↗ | — |
| Cached input / 1M | — | $0.5 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $35 | — |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-04-02 | 2026-04-23 | — |
| Cited benchmark scores | 6 | 21 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Gemma 4 31B vs …
Models sharing the most benchmarksMore matchups
GPT-5.5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemma 4 31B and GPT-5.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.