Ripple-65B Preview price cut (13 Nov 2026)
Ripple-65B Preview got cheaper. 5 price changes, 92 new benchmark results. Daily digest for 13 Nov 2026. What changed in AI scores, prices and ranks.
BenchLeader refreshed 1704 models from 29 of 29 data feeds (benchmark publishers, aggregators and price lists). 5 price changes, 92 new or updated benchmark results across 29 data feeds.
Price changes
- DeepSeek V4 Pro (high) input price moved from $0.66/M to $1.32/M (100% up). (details)
- DeepSeek V4 Pro (high) output price moved from $1.98/M to $3.96/M (100% up). (details)
- Mistral Large 3 cached input price moved from $0.050/M to $0.070/M (40% up). (details)
- Ripple-65B Preview input price moved from $0.20/M to $0.10/M (50% down). (details)
- Ripple-65B Preview output price moved from $0.60/M to $0.30/M (50% down). (details)
New benchmark results
- Terminal-Bench: 18 new results, including Claude Fable 5.2, GPT-6.1 Terra, Gemini 4 Hydrogen… (board)
- HiL-Bench: 2 new results, including Gemini 4 Carbon, Kimi K3.1 Pro (board)
- AA Intelligence Index v5.0.1: 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- Humanity's Last Exam (AA): 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- HLE-Diamond (AA): 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- AA-LCR v1.1: 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- SciCode (AA): 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- AA-Omniscience v1.1: 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- CritPt: 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- CritPt v2 hard subset (AA): 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- GDPval-AA v2.1: 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
- Terminal-Bench 4.0 (AA): 2 new results, including Gemini 4 Argon, DeepSeek V4 Pro (board)
Score revisions
- GPT-6.1 Sol (max) on Design Arena Agentic: 1400 → 1420. (details)
- Claude Fable 5.2 on Design Arena Agentic: 1355 → 1368. (details)
- Gemini 4 Argon (high) on Arena Maths: 1531 → 1536. (details)
- Claude Opus 5.5 (high) on Design Arena Agentic: 1436 → 1408. (details)
- Gemini 4 Argon on Design Arena Agentic: 1269 → 1262. (details)
- Gemini 4 Carbon on Design Arena Website: 1293 → 1324. (details)
- Gemini 4 Carbon on Design Arena Agentic: 1308 → 1298. (details)
- Muse Wonder (max) on Design Arena Agentic: 1154 → 1159. (details)
- DeepSeek V4.1 Flash 1017 (max) on OpenRouter token share: 25.7% → 26.6%. (details)
- Mistral Large 4 on Arena Maths: 1465 → 1459. (details)
- DeepSeek V4.1 Flash 1017 (high) on OpenRouter token share: 25.7% → 26.6%. (details)
- Mistral Large 4 (high) on MirrorCode: 27.8% → 40%. (details)
- DeepSeek V4.1 Flash 1017 (no reasoning) on OpenRouter token share: 25.7% → 26.6%. (details)
- Nemotron 3.5 Lightning on OpenRouter token share: 0% → 0.5%. (details)
- DeepSeek V4.1 Flash 1017 on OpenRouter token share: 25.7% → 26.6%. (details)
- GPT-6.1 Terra on Design Arena Agentic: 1194 → 1187. (details)
- Grok 4.7 on Design Arena Agentic: 1245 → 1271. (details)
- DeepSeek V4.1 Flash 1017 (low) on OpenRouter token share: 25.7% → 26.6%. (details)
- Beam 1.0 (max) on Design Arena Website: 1245 → 1239. (details)
- DeepSeek V4.1 Flash 1017 (medium) on OpenRouter token share: 25.7% → 26.6%. (details)
- …and 1 more.
Speed changes
- Gemini 4 Carbon time to first token changed from 3.66 s to 6.69 s. (details)
- GPT-6 Astra time to first token changed from 3.23 s to 5.22 s. (details)
- GPT-5.6 Sol time to first token changed from 4.19 s to 2.24 s. (details)
- Muse Wonder time to first token changed from 2.24 s to 3.36 s. (details)
- Kimi K3.1 Pro time to first token changed from 1.04 s to 2.18 s. (details)
- Muse Spark 1.3 output speed changed from 212 tok/s to 98 tok/s. (details)
- GPT-5.6 Terra time to first answer changed from 20.72 s to 30.00 s. (details)
- Kimi K2.5 time to first token changed from 0.79 s to 1.21 s. (details)
- Kimi K3 output speed changed from 51 tok/s to 81 tok/s. (details)
- Qwen3.8 Max time to first token changed from 5.12 s to 2.86 s. (details)
- Grok 4.20 Multi-Agent time to first token changed from 11.81 s to 16.72 s. (details)
- GPT-5 time to first token changed from 7.73 s to 4.60 s. (details)
- Qwen3.5 Plus time to first token changed from 2.58 s to 0.86 s. (details)
- Claude Haiku 5.5 time to first token changed from 0.98 s to 1.37 s. (details)
- MiniMax M2.7 thinking time changed from 18.08 s to 10.80 s. (details)
- …and 74 more.
Today's top five
- Claude Fable 5.2 (max) — 72.7
- Gemini 4 Carbon (high) — 68.9
- Claude Opus 5.5 (max) — 68.4
- GPT-6 Astra (max) — 67.3
- Claude Fable 5.1 (max) — 66.7
More: New AI model releases this week, and the full LLM leaderboard 2026.
This digest is generated automatically from the day's data changes. Every line links to the page where you can check the numbers and their source.