Gemini
A family is a named generation or product line. Scores below are the sum of its named releases and any documented internal systems in the same line.
Benefit
+5.60
Harm
0.00
Net Good
5.60
Releases
Leaderboard
| Rank | Model | Organization | Benefit | Harm | Net | Events | Last impact |
|---|---|---|---|---|---|---|---|
| 8 | Gemini 3.1 Pro | Google DeepMind | +4.13 | 0.00 | 4.13 | 1 | 21 May 2026 |
| 34 | Gemini | Google DeepMind | +1.13 | 0.00 | 1.13 | 1 | 14 May 2025 |
| 53 | Gemini Deep Think | Google DeepMind | +0.27 | 0.00 | 0.27 | 1 | 11 Feb 2026 |
| 63 | Gemini 2.0 | Google DeepMind | +0.04 | 0.00 | 0.04 | 1 | 19 Feb 2025 |
| 64 | Gemini 3.0 Flash | Google DeepMind | +0.03 | 0.00 | 0.03 | 1 | 21 May 2026 |
Timeline
- Benefit
- Harm
- Net
Events
AlphaProof Nexus produces Lean proofs for nine Erdős instances and 44 OEIS conjectures
A 21 May 2026 DeepMind preprint reports formal proofs for nine of 353 Erdős problem instances and 44 of 492 OEIS conjectures, plus research collaborations. Its Gemini-led agents publish Lean artifacts; independent records distinguish full, partial, and variant results.
Aletheia, powered by Gemini Deep Think, solves several Erdős items and writes an eigenweights paper
On 11 February 2026 DeepMind reported that Aletheia, a math agent on Gemini Deep Think, autonomously solved Erdős 1051 (motivating a generalization), disproved clauses of Erdős 1040 and a strong pinned-distance form of 654, and generated a publishable arithmetic-geometry paper on eigenweights without human intervention.
Gemini Deep Think reaches IMO 2025 gold-medal standard
In July 2025, Google DeepMind’s Gemini Deep Think was officially graded at 35/42 on the IMO 2025 paper under contest-style conditions.
AlphaEvolve reports a rank-48 4x4 complex matrix-multiplication tensor and Google infrastructure tweaks
DeepMind’s Gemini-powered AlphaEvolve evolutionary coding agent, announced in May 2025, reported a rank-48 decomposition for 4×4 complex matrix multiplication and internal data-center and training-kernel changes.
Gemini-based AI co-scientist proposes liver-fibrosis targets later tested in organoids
Google’s multi-agent AI co-scientist, built on Gemini 2.0, proposed epigenetic targets and drugs for liver fibrosis; Stanford collaborators reported anti-fibrotic activity of vorinostat and BRD4 inhibitors in human hepatic organoids.