Mistral AI reports Mistral Large 4 results on AutomationBench across 657 workflows

MMistral AI10/7/2026, 07:33:03

Mistral AI evaluated Mistral Large 4 on AutomationBench, testing 657 business workflows across simulated workplace applications including Gmail, Google Sheets, Slack, and Salesforce.

According to Mistral AI, Mistral Large 4 finished ahead of competing models including Kimi K3, MiMo-V2.6-Pro, and DeepSeek V4 Pro.

#mistral-ai #mistral-large-4 #benchmarks

View original post ↗

Previous articleMistral AI reports Mistral Large 4 as top open-source model on Harvey's Legal Agent Benchmark Next articleAdithya S K introduces RL Environment Explorer on Hugging Face Hub

Related AI news

Mistral Large 4 solves 18 of 19 challenges in cybersecurity CTF speedrun

Mistral AI reported that Mistral Large 4 solved 18 out of 19 challenges in a Capture the Flag speedrun using tool calls grounded in actual runs.

MMistral AI•10/6/2026, 11:32:38•

#mistral-ai #mistral-large-4 #cybersecurity #benchmarks

Mistral AI reports Mistral Large 4 as top open-source model on Harvey's Legal Agent Benchmark

Mistral AI stated that Mistral Large 4 ranked as the number one open-source model on Harvey's Legal Agent Benchmark.

MMistral AI•10/7/2026, 07:35:05•

#mistral-ai #mistral-large-4 #benchmark

Mistral AI unveils Mistral Large 4 with 1T parameters and immediate API access

Mistral AI announced Mistral Large 4, a 1-trillion parameter natively multimodal model with 49 billion active parameters. The model is available now via API and Mistral Cloud infrastructure, ahead of an open weights release planned for late October.

MMistral AI•10/6/2026, 06:26:28•

#mistral-ai #mistral-large-4 #multimodal-ai #open-weights

Mistral AI demonstrates Mistral Large 4 reverse-engineering malware in 12 minutes

Mistral AI demonstrated Mistral Large 4 analyzing an unknown binary end-to-end, identifying the sample as Cobalt Strike, extracting IoCs and configuration, and generating a YARA rule report in 12 minutes.

MMistral AI•10/6/2026, 11:31:40•

#mistral-large-4 #cybersecurity #malware-analysis

Mistral Large 4 enters Code Arena: WebDev leaderboard at 45th place

Mistral Large 4 scored 1,534 points to rank 45th on Arena.ai's Code Arena: WebDev leaderboard, placing within 2 points of Claude Opus 4.8 (High) at nearly one-sixth the blended token cost.

AArena.ai•10/6/2026, 23:29:25•

#mistral-large-4 #arena.ai #mistral-ai #benchmarks

Reset history AI News FAQ Usage limits RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.

Data & original project: Did Codex Reset · Licoy