399B sparse MoE (13B active), Apache 2.0. Impressive score but one user reports 60% failure rate on production constraint-following tasks. Self-reported by Arcee.

Current #1 on LiveCodeBench leaderboard. Ahead of DeepSeek V3.2 Speciale (88.7).

Pass@1 with chain-of-thought. Temporary API-only reasoning variant. Gold-level results in IMO, ICPC World Finals, IOI 2025.

27k thinking tokens. Extended reasoning variant.

Leads LiveCodeBench v6 at time of release. ByteDance frontier model with ICPC/IMO/CMO gold medals.

Top-4 on LiveCodeBench leaderboard. Strong agentic coding model with 1M context window.

Reaches 88.9 with PaCoRe. Open-weight model competitive with frontier closed models on live coding.

LiveCodeBench v6, 64k token budget. Highest open-source score on this benchmark. Averaged over 5 runs.

LiveCodeBench v6. Highest open-weight LiveCodeBench score, beats most proprietary models.

LiveCodeBench v6. Outperforms GPT-5.2 and Claude Opus 4.5 on 80% of evaluated categories.

Pass@1 with chain-of-thought. Open-weight.

Strong competitive coding despite being the mid-tier variant.

Dense 27B model, all params active. Matches GPT-5-mini on SWE-bench. Best coding score in Qwen 3.5 medium lineup.

Official Google model card. 31B dense model on LiveCodeBench v6.

MoE variant. v6. Dense 31B scores 80.0%.

Competitive coding on real-world problems. Behind Gemini 3 Pro Preview (91.7%) and DeepSeek V3.2 Speciale (88.7%).

Standard (non-thinking) mode. Thinking mode reaches 83.3%. Speciale variant hits 88.7%.

Budget-tier model at $0.25/1M input tokens. Competitive coding despite being Google fastest/cheapest model.

India's first domestically-trained 105B model. MoE with 10.3B active params. Apache 2.0.

v6. Outperforms Qwen3 (66.0%) and GPT-OSS (61.0%) at same size class.

9B params. Competitive coding for a small model, though lags behind larger models (GPT-OSS-120B: 82.7).

48B MoE, 2.7B active params. Surpasses GLM-4.7-Flash-Thinking by 2.4% with 85% fewer tokens. Uses FiberPO RL algorithm.

v6 benchmark. Decent coding for a 3.6B active param model.

Competitive coding ability for 4B params. Open-weight, Apache 2.0.

Competitive coding for a 4B model. Runs on consumer edge hardware.

v6. Effective 2B params. Surpasses Gemma 3 27B on coding despite 10x fewer active parameters.

pass@1 on LiveCodeBench (10/01/2024-02/01/2025). Far behind frontier models like Gemma 4 31B (80%) on coding.

pass@1. Significantly behind frontier coding models.