PulseAugur
EN
LIVE 18:20:34

LLM benchmarks reveal performance across GPQA, SciCode, and reasoning tasks

By PulseAugur Editorial · [6 sources] ·

Independent benchmarks reveal the performance of several large language models across various metrics. Muse Spark Open achieved 89% on GPQA and 58.4% on SciCode, while Muse Glimmer scored 83.5% on GPQA and 44.9% on SciCode. Kimi K3.1 Pro demonstrated strong performance in long-context reasoning at 86.3% and SciCode at 60.8%. Qwen3.8 Max led in GPQA with 92.8% and showed 80.3% in long-context reasoning. AI

IMPACT Provides comparative performance data for LLMs on key benchmarks, aiding in model selection and development.

RANK_REASON The cluster reports benchmark results for multiple LLMs, which falls under research.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 6 sources. How we write summaries →

LLM benchmarks reveal performance across GPQA, SciCode, and reasoning tasks

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster reports benchmark results for multiple LLMs, which falls under research.
Source corroboration
6 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
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
10 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+2 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [6]

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

    📊 MiMo-V2.6-Pro — the actual numbers Humanity's Last Exam: 49.4% Long Context Reasoning: 86.3% SciCode: 60.9% ⚡ 38.1 tokens/sec 💰 55 intelligence points per dol

    📊 MiMo-V2.6-Pro — the actual numbers Humanity's Last Exam: 49.4% Long Context Reasoning: 86.3% SciCode: 60.9% ⚡ 38.1 tokens/sec 💰 55 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI

    LINKS olud.ai/leaderboard.html
  2. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    📊 Mistral Small 4 (Reasoning) — the actual numbers GPQA: 76.9% Humanity's Last Exam: 9.9% Long Context Reasoning: 49.7% SciCode: 38.8% ⚡ 159 tokens/sec 💰 16.4 i

    📊 Mistral Small 4 (Reasoning) — the actual numbers GPQA: 76.9% Humanity's Last Exam: 9.9% Long Context Reasoning: 49.7% SciCode: 38.8% ⚡ 159 tokens/sec 💰 16.4 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benc…

    LINKS olud.ai/leaderboard.html
  3. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    📊 Muse Spark Open (Xhigh) — the actual numbers GPQA: 89% Humanity's Last Exam: 43.9% Long Context Reasoning: 78.3% SciCode: 58.4% ⚡ 190.5 tokens/sec 💰 12.4 inte

    📊 Muse Spark Open (Xhigh) — the actual numbers GPQA: 89% Humanity's Last Exam: 43.9% Long Context Reasoning: 78.3% SciCode: 58.4% ⚡ 190.5 tokens/sec 💰 12.4 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchma…

    LINKS olud.ai/leaderboard.html
  4. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    📊 Muse Glimmer (High) — the actual numbers GPQA: 83.5% Humanity's Last Exam: 22% Long Context Reasoning: 83.3% SciCode: 44.9% ⚡ 116.7 tokens/sec 💰 12 intelligen

    📊 Muse Glimmer (High) — the actual numbers GPQA: 83.5% Humanity's Last Exam: 22% Long Context Reasoning: 83.3% SciCode: 44.9% ⚡ 116.7 tokens/sec 💰 12 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # …

    LINKS olud.ai/leaderboard.html
  5. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    📊 Kimi K3.1 Pro — the actual numbers Humanity's Last Exam: 52.5% Long Context Reasoning: 86.3% SciCode: 60.8% ⚡ 29 tokens/sec 💰 11.5 intelligence points per dol

    📊 Kimi K3.1 Pro — the actual numbers Humanity's Last Exam: 52.5% Long Context Reasoning: 86.3% SciCode: 60.8% ⚡ 29 tokens/sec 💰 11.5 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI

    LINKS olud.ai/leaderboard.html
  6. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    📊 Qwen3.8 Max (0902) — the actual numbers GPQA: 92.8% Humanity's Last Exam: 43.1% Long Context Reasoning: 80.3% SciCode: 52.1% ⚡ 38.1 tokens/sec 💰 11.2 intellig

    📊 Qwen3.8 Max (0902) — the actual numbers GPQA: 92.8% Humanity's Last Exam: 43.1% Long Context Reasoning: 80.3% SciCode: 52.1% ⚡ 38.1 tokens/sec 💰 11.2 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks …

    LINKS olud.ai/leaderboard.html

RELATED ENTITIES

RELATED TOPICS