Haiku 5.5 Tops WebMCP Benchmark

// 1h agoBENCHMARK RESULT

Haiku 5.5 Tops WebMCP Benchmark

WindTunnel’s October 15 v1.3 update adds six model configurations, with Haiku 5.5 taking first on the composite WebMCP leaderboard at 98.3, ahead of GPT-6 Luna at 95.5. Across 49 tasks on eight real web apps, the benchmark blends success, cost, and latency into an agent-efficiency score.

// ANALYSIS

The surprise is less Haiku’s raw intelligence than the economics of tool calling: it combines perfect reliability with enough speed to beat Luna despite Luna’s lower per-task cost.

–Haiku achieved 147/147 successful attempts at a 3.7-second median; Luna achieved 144/147 at 5.0 seconds.
–Sonnet 5.5, GPT-6.1 Sol, Gemini 3.8 Flash, and Muse Wonder occupy a tightly packed second tier.
–The score weights success at 60%, cost at 20%, and time at 20%, rewarding dependable completion over isolated reasoning quality.
–WindTunnel’s authors also created the reference WebMCP tool implementations, a disclosed confounder that makes independent reproductions important.

// TAGS

windtunnelbenchmarkevaluationweb-agenttool-usemcp

DISCOVERED

1h ago

2026-10-15

PUBLISHED

2h ago

2026-10-15

RELEVANCE

9/ 10

AUTHOR

0xidanlevin

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE9m ago

FLUX 3 Image Klein Goes Open-Weight

Black Forest Labs’ FLUX 3 Image Klein brings box-guided layouts, multi-reference editing, style transfer, and text rendering to downloadable weights, with distilled and Base variants for fast inference and fine-tuning. It is available through fal.ai for text-to-image and editing, targeting local deployment on consumer hardware.

MODEL16m ago

NVIDIA Nemotron 3.5 Super VL Powers Agents

NVIDIA released Nemotron 3.5 Super VL, an open-weight 120B Mixture-of-Experts multimodal model with 12B active parameters for reasoning, tool use, and text, image, document, and video understanding. It is available through fal for building specialized agent workflows. [NVIDIA announcement](https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/)

NEWS27m ago

Daybreak cuts SentinelOne malware analysis to hours

OpenAI Daybreak gives SentinelOne governed access to frontier models for defensive cybersecurity workflows. SentinelOne says sophisticated malware reverse engineering that once took four to six weeks can now reach human-level output in roughly eight hours.