Mira Murati's Inkling Small Matches Flagship at 1/3 Parameters
ArtificialAnlys · x · 2026-07-31
Thinking Machines, founded by former OpenAI CTO Mira Murati, has released Inkling Small (276B total parameters, 12B active, Apache 2.0). Despite using less than a third of the flagship's parameters, it scores 40 on the Artificial Analysis Intelligence Index—just one point behind its larger sibling—making it the highest-scoring open weights model at its size.
Key Evaluation Findings:
- Coding & Reasoning: Meets or exceeds the flagship on several benchmarks, including HLE (32% vs. 30%), GPQA Diamond (89% vs. 87%), and SciCode (49% vs. 46%).
- Agentic & Factual: Compromises on factual accuracy with an AA-Omniscience score of -9 (vs. 2), but compensates with better presentation in long-horizon agentic tasks, achieving higher Elo.
- Token Efficiency: Averaged 24K output tokens per task, slightly fewer than the flagship and significantly more efficient than peers like DeepSeek V4 Flash (45K) and GPT-5.4 mini (78K).
- Pricing & Speed: Priced at $0.30/1M input and $1.20/1M output tokens, with a solid generation speed of 92 tokens/s.
Related event: Thinking Machines Releases Open-Source Inkling-Small Model(19 posts)→
More from Models
- Grok 2 Voice Mode Delayed? X Platform Silently Changes Release Window to 'Soon' — teortaxesTex · 2026-07-31
- Anthropic Launches Claude Opus 5: State-of-the-Art Performance at Half the Cost — dl_weekly · 2026-07-31
- Osmosis AI Bets on RL and YC GPU Cluster to Rival Foundation Models — togethercompute · 2026-07-31
- ChatGPT Rate Limit Quirk: No Self-Check and Independent of Codex — Sauers_ · 2026-07-31
- Annotator Ghost in the Weights: Opus 5 Channels Trainers in Base Mode — aiamblichus · 2026-07-31
- Google Rollsouts Gemini Robotics ER 2 Model via API — ericjang11 · 2026-07-31