Which model leads OlympiadBench?

Q: Which model leads OlympiadBench?

Gemini 2.0 Flash Exp tops the board at 46.1

OlympiadBench Leaderboard — Model Scores

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 7 measured

19.346.1

7 models measured, most on the official card harness. Gemini 2.0 Flash Exp tops the board at 46.1.

7 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 7Bars show 19.3–46.1 · ◆ solid = first-party or better · outlined = arm's-length

01Gemini 2.0 Flash ExpGoogle46.1———

02Gemini 1.5 Pro+1 altGoogle32.1———

03Claude 3.5 Sonnet+1 altAnthropic28.4$3.0/M$15.0/M$0.317

04GPT-4o+1 altOpenAI25.2$5.0/M$15.0/M$0.397

05InternVL2.5-78BOpenGVLab25.1———

06MiniMax VL 01MiniMax24.2———

07Llama 3.2 Instruct 90B (Vision)Meta19.3———

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 7 models scored · 0 independently verified · 6 vendor cross-reference · 1 vendor-reported · 0 with source disagreement. How these tiers are assigned