Inklingopen
Thinking Machines
37.9#279 of 427 overall
- Input / output
- US$ 1,00 / US$ 4,05 US$ per 1M tokens
- Context
- 524K tokens
- Release
- 07/17/2026 release date
- Speed
- 150 tok/s first token in 2.00 s
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| LiveBench weight 3 | 47.1 | 10% | LiveBench |
| AA Intelligence Index weight 3 | 12.5 | 19% | Artificial Analysis |
| Arena text (Elo) weight 2 | 1443 | 73% | LMArena |
| Arena WebDev (Elo) weight 1 | 1415 | 37% | LMArena |
| Humanity's Last Exam weight 1 | 31.9 | 81% | Artificial Analysis |
| Terminal-Bench weight 1 | 1.0 | 56% | Artificial Analysis |
| GPQA Diamond | 87.2 | 84% | Artificial Analysis |
| Long-context reasoning | 77.3 | 77% | Artificial Analysis |
| LiveBench long agentic | 8.5 | 7% | LiveBench |
| LiveBench reasoning | 78.3 | 19% | LiveBench |
| LiveBench coding | 64.0 | 16% | LiveBench |
| LiveBench browser | 12.0 | 7% | LiveBench |
| LiveBench data analysis | 72.8 | 36% | LiveBench |
| LiveBench research | 59.9 | 13% | LiveBench |
| LiveBench design | 58.3 | 3% | LiveBench |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 37.5 | #81 | LiveBench long agentic, Terminal-Bench |
| Coding | 34.4 | #95 | LiveBench coding, Arena WebDev (Elo) |
| Reasoning | 58.5 | #159 | LiveBench reasoning, Humanity's Last Exam, GPQA Diamond |
| Data analysis | 42.8 | #21 | LiveBench data analysis |
| Research | 46.6 | #200 | LiveBench research, Long-context reasoning |
| Design | 30.1 | #106 | LiveBench design, Arena WebDev (Elo) |
| Browser use | 28.3 | #30 | LiveBench browser |
| Chat | 61.4 | #55 | Arena text (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.