PulseAugur
EN
LIVE 22:18:08

Mistral Large 4 trails competitors on DeepSWE v1.1 coding benchmark

By PulseAugur Editorial · [1 sources] ·

Mistral Large 4 has demonstrated a performance of 61.7% on the DeepSWE v1.1 benchmark for coding tasks. This score places it behind both Chinese open-weight models, which achieved approximately 69%, and leading closed-source models from OpenAI, Google, and Anthropic, which scored around 74%. The data indicates that performance gaps continue to exist, even as open-weight models see increased development and availability. AI

IMPACT Mistral Large 4's performance on coding benchmarks indicates areas for improvement compared to leading closed-source and some open-weight models.

RANK_REASON The item reports on benchmark results for a specific AI model, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Mistral Large 4 trails competitors on DeepSWE v1.1 coding benchmark

How we ranked this

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item reports on benchmark results for a specific AI model, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · schuler ·

    On coding tasks, Mistral Large 4 scores 61.7% on DeepSWE v1.1—trailing both open models from China (around 69%) and closed models from OpenAI, Google, and Anthr

    On coding tasks, Mistral Large 4 scores 61.7% on DeepSWE v1.1—trailing both open models from China (around 69%) and closed models from OpenAI, Google, and Anthropic (around 74%). Performance gaps persist even as open-weight models expand. https://www. implicator.ai/mistral-large-…

    LINKS implicator.ai/mistral-large-4-open-weight…

RELATED ENTITIES

RELATED TOPICS