Proximal is a research lab focused on data.
Proximal is a new data company. Our core belief is that data which is complex enough to teach today’s frontier models is not bottlenecked by domain experts, but by research, great systems, and excellent software. We are not a recruiting firm or a talent marketplace, but a research and engineering organization that treats data as a problem which deserves the same level of rigor as work on training algorithms and model architectures.
We think that this is the most impactful work towards agents that can autonomously solve complex technical problems, and intend to share our research and progress in the open.
Announcements, benchmark releases, and the work behind both.
Research & Engineering•9 min read
FrontierSWE
Our ultra-long-horizon coding benchmark. Frontier models clear only a fraction of its tasks.
| # | Model | Harness | Avg Rank¹ | Dominance² | Implementation | Performance | Research |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5Claude Code | Claude Code | 2.88 | 88% | 2.00 | 2.00 | 7.00 |
| 2 | GLM-5.3Claude Code | Claude Code | 4.50 | 78% | 4.00 | 5.83 | 1.33 |
| 3 | Grok 4.6Grok CLI | Grok CLI | 4.53 | 78% | 3.30 | 5.39 | 4.00 |
| 4 | Grok 4.5Grok CLI | Grok CLI | 5.47 | 72% | 6.20 | 5.67 | 3.67 |
| 5 | GLM-5.2Claude Code | Claude Code | 6.21 | 67% | 6.30 | 7.00 | 3.67 |
| 6 | Claude Opus 4.8Claude Code | Claude Code | 6.35 | 67% | 5.40 | 6.56 | 7.33 |
| 7 | GPT-5.5Codex | Codex | 6.68 | 65% | 8.80 | 5.11 | 7.83 |
| 8 | Claude Opus 4.7Claude Code | Claude Code | 8.00 | 56% | 7.20 | 8.33 | 8.33 |
| 9 | Claude Opus 4.6Claude Code | Claude Code | 9.18 | 49% | 9.20 | 9.11 | 9.33 |
| 10 | GPT-5.4Codex | Codex | 9.65 | 46% | 8.70 | 11.06 | 7.00 |
| 11 | Gemini 3.1 ProGemini CLI | Gemini CLI | 11.50 | 34% | 13.80 | 9.06 | 15.00 |
| 12 | Composer 2.5Cursor CLI | Cursor CLI | 11.59 | 34% | 10.20 | 13.39 | 8.50 |
| 13 | GLM-5.1Claude Code | Claude Code | 12.88 | 26% | 12.90 | 12.94 | 12.67 |
| 14 | DeepSeek V4 ProClaude Code | Claude Code | 13.06 | 25% | 13.00 | 13.11 | 13.00 |
| 15 | Kimi K2.5Kimi CLI | Kimi CLI | 13.26 | 23% | 14.50 | 11.78 | 15.67 |
| 16 | Kimi K2.6Kimi CLI | Kimi CLI | 13.44 | 22% | 11.70 | 14.44 | 13.33 |
| 17 | Qwen3.6-PlusQwen Code | Qwen Code | 13.82 | 20% | 15.80 | 12.22 | 15.33 |
Research & Engineering•7 min read
Our Problems
An overview of the problems we’re working on at Proximal.
Read more →Company•4 min read
Announcing Proximal
We believe data is becoming one of the central research problems in AI, and no one is working on it the right way. Proximal is a research lab for data.
Read more →We're hiring across research and engineering.
If treating data as a first-class research problem sounds like the work you want to be doing, we'd like to hear from you.
