Which model leads DynaMath?

Q: Which model leads DynaMath?

Qwen3.6 Plus tops the board at 88

DynaMath Leaderboard — 14 Models Ranked

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

The field · 11 measured

61.588

11 models measured, most on the official card harness. Qwen3.6 Plus tops the board at 88.

11 measured·Lifecycle Updated Oct 17, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 11Bars show 61.5–88 · ◆ solid = first-party or better · outlined = arm's-length

01Qwen3.6 PlusAlibaba88$0.50/M$3.0/M$0.020

02Qwen3.5 27BAlibaba87.7$0.30/M$2.4/M$0.015

03Qwen3.5 122B A10BAlibaba85.9$0.40/M$3.2/M$0.021

04Qwen3.6 27BAlibaba85.6$0.60/M$3.6/M$0.025

05Qwen3.5 35B A3BAlibaba85$0.25/M$2.0/M$0.013

06GPT-5.5OpenAI75.9$5.0/M$30.0/M$0.231

07Seed 2.1 Pro Preview+1 altByteDance73.1———

08Gemini 3.1 ProGoogle72.1$2.0/M$12.0/M$0.097

09Seed2.1ByteDance68.1———

10Claude Opus 4.7Anthropic63.1$5.0/M$25.0/M$0.238

11Seed 1.8ByteDance61.5$0.25/M$2.0/M$0.018

◆ 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: 11 models scored · 0 independently verified · 3 vendor cross-reference · 8 vendor-reported · 0 with source disagreement. How these tiers are assigned