Step 5 Preview scores 32.83 on Hermes Index, trailing GPT-6 Luna and GLM 5.3 Flash
NousResearch · x · 2026-10-10
NousResearch corrected the final Hermes Index score of StepFun's Step 5 Preview to 32.83, slightly behind GPT-6 Luna (33.89) and GLM 5.3 Flash (34.95) — an update from the earlier claim it tied GPT-6 Luna.
Key details:
- Step 5 Preview is a 600B-total / 27B-active MoE model with 1M context and vision, free on Nous Portal for the next week.
- Top of the Hermes Index: Claude Opus 5.5 leads at 63.31 ($4.99 avg per task), GPT-6 Astra second at 56.25 ($11.61), Claude Sonnet 5.5 third at 53.14 ($2.82).
- The benchmark runs inside Hermes Agent and scores task completion and cost per task across four suites.
Related event: StepFun's Step 5 Preview Opens Free for a Week(2 posts)→
More from Models
- Gemini 4 Argon tops deepswe at 77.9% and automationbench, still locked to trusted testers — weswinder · 2026-10-10
- TWIML podcast: TypeSafe's Jev model bets on machine-native intelligence over LLMs — samcharrington · 2026-10-10
- Anthropic starts frequent behavior reports, detailing four unintended Claude actions — AnthropicAI · 2026-10-10
- Cloudflare releases clef-omni, an open omni-modal model with audio, image and video input — ritakozlov · 2026-10-10
- Strong backbones plus light fine-tuning beat synthetic data, says researcher whose model tops benchmarks — antoine_chaffin · 2026-10-10
- AWS Bedrock posts legacy notices for Claude Opus 4.1, Sonnet 4 and Sonnet 4.5 — repligate · 2026-10-10