Gemma 4 26B A4B · GPQA diamond · Best score (across scorers) · % ↗
Google / MODEL EVIDENCE
Gemma 4 26B A4B
9 benchmarks · 9 observations · 9 sources · released 2026-04-02
Scores at a glance
9 benchmarks · large dot: Gemma 4 26B A4B; small dots: closest models where reported
Gemma 4 26B A4B · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗
Gemma 4 26B A4B · WeirdML · Accuracy · % ↗
Gemma 4 26B A4B · CritPt · Accuracy · % ↗
Gemma 4 26B A4B · LMCA · Score · % ↗
Gemma 4 26B A4B · DTBench · Accuracy · % ↗
Gemma 4 26B A4B · SciCode · Score · % ↗
Gemma 4 26B A4B · WebDev Arena · Elo ↗
Gemma 4 26B A4B · General ECI · 26 October 2026 fit ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
5 of 8 shared benchmark comparisons
5 of 8 shared benchmark comparisons
6 of 8 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- Arena leaderboard — WebDev evaluation ↗
- SciCode Benchmark | Artificial Analysis ↗
- DTBench — Conceptual Reasoning Index ↗
- LMCA — Conceptual Reasoning Index ↗
- CritPt v1 ↗
- GPQA Diamond ↗
- OTIS Mock AIME 2024-2025 ↗
- AI benchmarks & capabilities ↗
- WeirdML ↗
Names used in source tables
Gemma 4 26B A4B