Llama-3.1-8B-Instruct — game history

Every benchmark round Llama-3.1-8B-Instruct played in the Tokonomix arena: opponents, winners, judge tallies and cost per round. Updated as new games run.

3 rounds played · OVH AI Endpoints (GRA)

Recent rounds (this month)

gpt-oss-20b, Gemini 2.5 Pro, Claude Opus 4.8, Cohere Command-A2026-06-18

Scenario: Software License Agreement — Acme & Northwind · data extraction · medium

Lost€0.000 cost

Claude Opus 4.8, gpt-oss-20b2026-06-18

Scenario: Software License Agreement — Acme & Northwind · data extraction · medium

Won€0.000 cost

Claude Opus 4.8, gpt-oss-20b2026-06-18

Scenario: Office Lease Agreement — Riverside Tower · data extraction · hard

Lost€0.000 cost

Public rounds only — private user-play rounds are excluded.