Claude Opus 5.5 tops SWE-bench Multimodal at 70.21%, nearly 9 points ahead
OfirPress · x · 2026-10-15
Vals AI launched the SWE-bench Multimodal leaderboard, testing whether AI systems generalize to visual software engineering (JavaScript issues reported with screenshots). Claude Opus 5.5 ranks first at 70.21%, ahead of Claude Fable 5.1 (61.25%) and Claude Sonnet 5.5 (58.33%).
Other takeaways:
- Per-task cost varies wildly: $0.03 for GPT-6 Luna vs $11.40 for Gemini 4 Argon
- DeepSeek V4.1 Flash offers standout value: 46.46% at $0.23/task
- Kimi K3 scores 35.83%, Grok 4.7 42.92%, Qwen 3.8 Max 39.17%
- Scores spread widely from 35.83% to 70.21%, showing a large frontier-vs-rest gap
Related event: SWE-bench Multimodal Leaderboard Debuts, Claude Opus 5.5 Leads at 70.21%(4 posts)→
More from coding & agent
- Creator builds custom GoPro ingestion tool with Codex: 4-camera array with WiFi trickle ingest — OpenAIDevs · 2026-10-15
- HybridAgent reasons in latent space, acts via text — 2x faster, 3x cheaper, open-sourced — zainhas · 2026-10-15
- Claude Code 2.1.300 ships 88 CLI changes, drops AskUserQuestion directive from system prompt — ClaudeCodeLog · 2026-10-15
- Tahoe AI opens Tara, a one-prompt plug-in connecting agents to its Tahoe-100M biology datasets — anshulkundaje · 2026-10-15
- sgrep cuts coding agent LLM costs 21.3% on SWE-bench versus ripgrep, fully local in Rust — udmrzn · 2026-10-15
- 10 GitHub repos that turn Claude Code and Codex into elite UI designers — udmrzn · 2026-10-15