Google, released Mar 12, 2025

Gemma 3 27B ITprice, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 74% confidence 74 percent, Medium confidence, 4 of 9 expected sources in
42.0
SI Score
#122 of 142 ranked models
Input, per 1M tokens
not yet reported
Output, per 1M tokens
not yet reported
Context window
131Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
131Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Mar 12, 2025models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

How the score breaks down

Coding (weight 40 percent) 8.1
Math (weight 15 percent) 56.9
Preference (weight 15 percent) 68.8
Reasoning (weight 30 percent) 47.7

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.

Around it on the leaderboard

  1. 120 Gemma 3 12B IT 45.1
  2. 121 GPT-4o (2024-11-20) 42.2
  3. 122 Gemma 3 27B IT 42.0
  4. 123 o3-mini 41.6
  5. 124 GPT-4.1 41.5

Full leaderboard

Benchmark results

6 benchmarks, 6 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

GPQA Diamondreasoning 47.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 47.7
MATH Level 5math 74.0%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Mar 13, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 74.0
OTIS Mock AIME 2024–2025math 22.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 22.5
Aider Polyglotcoding 4.9%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Mar 15, 2025 Retrieved Oct 9, 2026 · Apache-2.0
Open source ↗ 4.9
SWE-bench Pro (public)coding 11.4%SWE-bench Pro (public)Published steward score [variant] Published Jan 27, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 11.4
LMArena Textpreference 1357.7 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 68.8

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights
Yesmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, imagemodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
First seen by SuperIndex
Oct 8, 2026
Coverage
59% of expected source weight

Reported (4)

  • Aider polyglotOct 8, 2026
  • Epoch AI BenchmarkingOct 8, 2026
  • LMArena / ArenaOct 8, 2026
  • SWE-bench Pro (public)Oct 8, 2026

Awaiting (5)

  • ARC Prize11% of weight
  • Humanity’s Last Exam11% of weight
  • Official model cards via models.dev4% of weight
  • LiveBench11% of weight
  • Terminal-Bench5% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed