togetherbench.com
togetherbench.com is SWE-Together: an interactive coding-agent evaluation benchmark built from real multi-turn coding sessions. 109 tasks across 36 public repositories.. It is ranked #311 on the AI Radar, in AI coding agents, first seen 2 h ago and shared in 1 post (2.8k views).
SWE-Together: Interactive Coding-Agent Evaluation Together Bench > _ < SWE-Together: Interactive Coding-Agent Evaluation Explore tasks → Paper Contact GitHub Leaderboard Model judge ↑ correction ↓ tokens min $ / task ↓ ★ Oracle reference ~78% 0.904 — — — — claude-fable-5 62% 70% 0.853 1.53 67.6k 29.3 $18.02 claude-fable-5.1 61% 69% 0.827 1.45 58.0k 23.4 $8.24 gemini-3.8-flash 55% 66% 0.829 1.57 92.5k 26.8 $4.15 grok-4.7 53% 65% 0.835 1.49 76.3k 25.5 $7.81 claude-opus-5 54% 64% 0.803 1.44 92.7k 30.4 $13.61 muse-spark-1.3 50% 63% 0.797 1.86 102.2k 25.7 $3.19 claude-opus-4.8 51% 62% 0.802 1.56 71.4k 21.3 $9.29 claude-opus-4.6 51% 62% 0.809…
What people said about togetherbench.com on X
Tiger Parenting and its consequences Elon demanded "beat Opus at any cost" and grok obliged
— @teortaxesTex, 2 h ago · 32 likes · see the post
Alternatives to togetherbench.com
- academy.dair.ai — Chat with Paper
- zcode — Z.ai's coding agent harness. Powerful, intelligent, extensible. - zai-org/ZCode
- Probably — Introducing Probably: a programming language powered by Jev
- Grok Build — Grok Build is now powered by Grok 4.6, our newest model — with a native subagent view, Plan Mode integration, mouse…
- Pi Coding Agent — We also pushed out a new release so that the library can use the latest models.
- step-code — Contribute to stepfun-ai/Step-Code development by creating an account on GitHub.
togetherbench.com in numbers
- Rank on the AI Radar: #311 of 1818
- Shared in 1 post by 1 account: @teortaxesTex
- 2.8k views on those posts
- First seen 2 h ago, last shared 2 h ago
- Pricing seen by Jev: not stated
- Market: AI coding agents
FAQ
What is togetherbench.com?
SWE-Together: an interactive coding-agent evaluation benchmark built from real multi-turn coding sessions. 109 tasks across 36 public repositories. It was first shared on X 2 h ago and is ranked #311 on the AI Radar.
Is togetherbench.com free?
Pricing is not stated on the page we read.
Who shared togetherbench.com?
1 account on X, including @teortaxesTex, in 1 post totalling 2.8k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 43.9k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 07:51 UTC. Full method.