With tools variant. No-tools score is 56.8%. 11.6 pts ahead of Opus 4.6 with tools (53.1%).

Highest self-reported HLE score. With tools. Leads GPT-5.2-Thinking by 28%. First Chinese model to top HLE.

Contemplating mode (multi-agent parallel reasoning). First model from Meta Superintelligence Labs. Accepts voice, text, image inputs. Strong multimodal + health, weaker on agentic tasks vs Mythos/GPT-5.4.

Without tools. 16.8pp above Opus 4.6 (40.0%). Strongest reasoning model on HLE.

Hardest reasoning benchmark. With tool use. Corrected score per Feb 23 update.

Strong HLE score, competitive with frontier models on this extreme reasoning test.

Tool-augmented evaluation variant. Base (no tools) score is 30.5%. Higher than Claude Opus 4.5 tools score.

With tool access. Nearly 2x the CoT-only score. Impressive for a 27B model — beats several frontier models.

Without tools. Google specialized reasoning mode. Also scored 84.6% on ARC-AGI-2.

Without tools. Google DeepMind official benchmarks page. Leads frontier models on HLE standard eval.

Top of Scale AI HLE leaderboard. Standard evaluation, no tools.

Open-weight model with tools, competitive with GPT-5.1 High (42.7%).

Second-highest on HLE behind GPT-5.4 Pro (44.3%). Codex-native agent combining frontier coding with general reasoning.

Second on Scale AI HLE leaderboard. Standard evaluation, no tools.

xhigh thinking config on Scale AI HLE leaderboard.

Standard evaluation on Scale AI HLE leaderboard.

Text-only subset. With tools: 50.4% (comparable to Kimi K2.5 51.8%).

Standard evaluation on Scale AI HLE leaderboard.

Chinese frontier model. Strong HLE showing for open-weight model.

Chain-of-thought only. With tools jumps to 48.5%. Shows HLE requires tool use for small models.

Frontier reasoning benchmark. Third-party verified via Artificial Analysis.

Without tools. Dense 31B model. Strong HLE for an open-weight model.

HLE without tools. Behind frontier models (Opus 4.6: 30.7, GPT-5.2: 31.4).

Without tools. 30B-A3B MoE, 3.6B active params.