Gemini 4 Carbon debuts #2 on Vals Index at half the cost, tops finance and legal benchmarks
zacharynado · x · 2026-10-29
Vals AI's Index v2.2 shows Gemini 4 Carbon debuting at #2 overall with 70.36% accuracy, just behind Claude Sonnet 5.5 (70.85%), while taking #1 on both the Finance Index and Legal Research Benchmark. Notably it costs $10.51 per test with 47m45s latency vs the leader's $18.70 and 1h26m. Claude Opus 5.5 ranks #3 at $28.12 per test; DeepSeek V4.1 Flash is cheapest at $0.66.
Related event: Vals AI Index: Claude Sonnet 5.5 Tops Rankings, Gemini 4 Carbon Second(3 posts)→
More from Models
- Rumor: Anthropic may scrap planned sub cuts or trade 5-hour limits for monthly usage caps — CtrlAltDwayne · 2026-10-29
- OpenAI lets ChatGPT Pro and Business subscribers claim up to $500/month in API credits — OpenAIDevs · 2026-10-29
- Researcher: GPT6 Astra brings a step change in review quality, guided prompts help further — anshulkundaje · 2026-10-29
- Paper Instruments launches Ultramarine 1 Flash, beating frontier models at up to 60x lower cost — baseten · 2026-10-29
- Gemini 4 reportedly "proved" nearly half of the false theorems it was given — RishabJainK · 2026-10-29
- Sentdex: DeepSeek v4.1 Flash now his top local token generator ever — Sentdex · 2026-10-29