Which model leads PopQA?

Q: Which model leads PopQA?

Llama 3.1 8B Instruct tops the board at 28.79

PopQA Leaderboard — Model Scores

Pro Mode — raw scores, one benchmark under the lensthird-party eval harness

The field · 9 measured

9.9428.79

9 models measured, most on the third-party eval harness. Llama 3.1 8B Instruct tops the board at 28.79.

9 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 9Bars show 9.94–28.79 · ◆ solid = first-party or better · outlined = arm's-length

01Llama 3.1 8B InstructMeta28.79$0.02/M$0.04/M$0.001

02Granite 3.1 8B InstructIBM28.7———

03Granite 3.2 8B InstructIBM28.04———

04Granite 3.3 8B Instruct+1 altIBM26.17VENDOR$0.03/M$0.25/M$0.005

05Granite 3.2 2B InstructIBM20.56———

06Granite 3.1 2B InstructIBM20.55———

07Granite 3.3 2B InstructIBM18.4———

08DeepSeek-R1-Distill-Llama-8BDeepSeek13.25$0.05/M$0.05/M$0.004

09DeepSeek-R1-Distill-Qwen-7BDeepSeek9.94$0.15/M$0.15/M$0.015

◆ 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: 9 models scored · 0 independently verified · 8 vendor cross-reference · 1 vendor-reported · 0 with source disagreement. How these tiers are assigned