Gemini 3 Flash TrueSkill µ = 30.1 ± 3.3 in 98 canonical games

The Bayesian skill posterior mean for G3-F is 30.1 with 3σ confidence interval ±3.3.

Source paper

extracted_from

(2026) · Robert Müller · Clemens Müller

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Gemini 3 Flash median final score 5,250 in 98 canonical gamesfinding0.869
G3-F's median score across games was 5,250 points.
Gemini 3 Flash wins 72.9% of 98 canonical gamesfinding0.851
G3-F achieved a win rate of 72.9% in the combined-comp1 98-game slice.
Gemini 3 Flash averages 3.96 quartets per gamefinding0.847
G3-F completed on average 3.96 quartets per game.
Gemini 3 Flash TC bargaining tightness τ ≈ 0.34finding0.816
G3-F achieves a TC tightness of about 0.34, meaning moderate overpayment in won challenges.
G3-F TrueSkill μ=30.1 ± 3.3, 72.9% wins, median score 5,250 on combined-comp1 slice (n=98 canonical games)finding0.808
Top LLM performance with high win rate and large score.
DS-v3.2 TrueSkill μ=23.9±2.7finding0.808
DeepSeek v3.2 TrueSkill rating
G3.1-FL TrueSkill μ=28.0 ± 2.9, 44.9% win ratefinding0.800
Second-best LLM, competitive with TrackerAgent.
Gemini 3 Flash wins 67.9% of its 28 mixed-format games against code agentsfinding0.800
In the 172-game exp2 slice, G3-F has the highest LLM win rate against deterministic baselines.