Nemotron 3.5 Bolt E4B added (15 Nov 2026)
Nemotron 3.5 Bolt E4B joins the board; Claude Fable 5.1 moved #9 → #7. 1 new model, 2 top-10 rank changes, 38 price changes, 633 new benchmark results.
BenchLeader refreshed 1718 models from 29 of 29 data feeds (benchmark publishers, aggregators and price lists). 1 new model, 2 top-10 rank changes, 38 price changes, 633 new or updated benchmark results across 29 data feeds.
New models
- Nemotron 3.5 Bolt E4B (thinking) (NVIDIA) appeared with 1 benchmark result. (details)
Movement in the top 10
- Claude Fable 5.1 (max) moved from #9 to #7 in the BenchLeader Index. (details)
- GPT-6 Astra moved from #7 to #9 in the BenchLeader Index. (details)
Price changes
- Inkling 2 Small cached input price moved from $0.060/M to $0.030/M (50% down). (details)
- Hy4 cached input price moved from $0.025/M to $0.021/M (16% down). (details)
- MiMo-V2.5-Pro cached input price moved from $0.20/M to $0.0043/M (98% down). (details)
- Qwen3.8 27B cached input price moved from $0.10/M to $0.085/M (15% down). (details)
- Beam 1.0 501B A23B input price moved from $0.40/M to $0.30/M (25% down). (details)
- Beam 1.0 501B A23B output price moved from $1.20/M to $1.00/M (17% down). (details)
- Qwen3.8 27B (xhigh) cached input price moved from $0.10/M to $0.085/M (15% down). (details)
- Qwen3.5-9B (thinking) cached input price moved from $0.060/M to $0.063/M (5% up). (details)
- Qwen3.8 27B (medium) cached input price moved from $0.10/M to $0.085/M (15% down). (details)
- Qwen3.5-35B-A3B cached input price moved from $0.15/M to $0.050/M (67% down). (details)
- Qwen3.5-9B (no reasoning) cached input price moved from $0.060/M to $0.063/M (5% up). (details)
- Qwen3.8 27B (low) cached input price moved from $0.10/M to $0.085/M (15% down). (details)
- Qwen3.5-35B-A3B (no reasoning) cached input price moved from $0.15/M to $0.050/M (67% down). (details)
- Nemotron 3.5 Super VL cached input price moved from $0.060/M to $0.020/M (67% down). (details)
- Qwen3.8 27B (no reasoning) cached input price moved from $0.10/M to $0.085/M (15% down). (details)
- Mistral Large 3 cached input price moved from $0.070/M to $0.050/M (29% down). (details)
- Qwen3.5-9B cached input price moved from $0.060/M to $0.063/M (5% up). (details)
- GPT-5.1-Codex-Mini (high) cached input price moved from $0.025/M to $0.030/M (20% up). (details)
- MiMo-V2.5-Pro (thinking) cached input price moved from $0.20/M to $0.0043/M (98% down). (details)
- Nemotron 3 Nano 30B A3B input price moved from $0.050/M to $0.060/M (20% up). (details)
- Nemotron 3 Nano 30B A3B output price moved from $0.20/M to $0.24/M (20% up). (details)
- Nemotron 3 Super 120B A12B input price moved from $0.30/M to $0.15/M (50% down). (details)
- Nemotron 3 Super 120B A12B output price moved from $0.90/M to $0.65/M (28% down). (details)
- Qwen3.5-35B-A3B (thinking) cached input price moved from $0.15/M to $0.050/M (67% down). (details)
- Inkling 2 Small (xhigh) cached input price moved from $0.060/M to $0.030/M (50% down). (details)
- MiMo-V2.5-Pro (no reasoning) cached input price moved from $0.20/M to $0.0043/M (98% down). (details)
- Nemotron 3.5 Super VL (no reasoning) cached input price moved from $0.060/M to $0.020/M (67% down). (details)
- GPT-5.1-Codex-Mini cached input price moved from $0.025/M to $0.030/M (20% up). (details)
- Nemotron 3.5 Super VL (medium) cached input price moved from $0.060/M to $0.020/M (67% down). (details)
- Nemotron 3.5 Super VL (high) cached input price moved from $0.060/M to $0.020/M (67% down). (details)
- …and 8 more.
New benchmark results
- LiveBench 2.0: 25 new results, including Claude Fable 5.2, Gemini 4 Carbon, Claude Opus 5.5… (board)
- LiveBench Long Agentic: 25 new results, including Claude Fable 5.2, Gemini 4 Carbon, Claude Opus 5.5… (board)
- LiveBench 2.0 Reasoning: 25 new results, including Claude Fable 5.2, Gemini 4 Carbon, Claude Opus 5.5… (board)
- LiveBench 2.0 Coding: 25 new results, including Claude Fable 5.2, Gemini 4 Carbon, Claude Opus 5.5… (board)
- LiveBench Browser: 25 new results, including Claude Fable 5.2, Gemini 4 Carbon, Claude Opus 5.5… (board)
- LiveBench 2.0 Data Analysis: 25 new results, including Claude Fable 5.2, Gemini 4 Carbon, Claude Opus 5.5… (board)
- LiveBench Research: 25 new results, including Claude Fable 5.2, Gemini 4 Carbon, Claude Opus 5.5… (board)
- LiveBench Design: 25 new results, including Claude Fable 5.2, Gemini 4 Carbon, Claude Opus 5.5… (board)
- Aider Polyglot: 25 new results, including GPT-5, GPT-5, DeepSeek V3.2… (board)
- Vibe Code Bench v1.1: 13 new results, including Claude Opus 5.5, Claude Fable 5.2, Claude Fable 5.1… (board)
- Legal Research Bench: 11 new results, including Claude Opus 5.5, Claude Fable 5.2, Claude Fable 5.1… (board)
- MedCode: 11 new results, including Claude Opus 5.5, Claude Fable 5.1, Claude Fable 5… (board)
Score revisions
- GPT-6.1 Sol (max) on Design Arena Agentic: 1370 → 1375. (details)
- Claude Fable 5.1 on Design Arena Agentic: 1333 → 1338. (details)
- Claude Opus 5.5 (high) on Design Arena Agentic: 1449 → 1454. (details)
- GPT-6 Astra (xhigh) on Design Arena Agentic: 1299 → 1304. (details)
- Claude Opus 5 on Design Arena Agentic: 1266 → 1271. (details)
- Claude Opus 4.6 on Design Arena Agentic: 1192 → 1197. (details)
- Kimi K3.1 Pro on Design Arena Agentic: 1296 → 1301. (details)
- GPT-5.5 on Design Arena Agentic: 1109 → 1114. (details)
- Claude Opus 5.5 on Design Arena Agentic: 1334 → 1339. (details)
- Muse Wonder (max) on Design Arena Agentic: 1168 → 1177. (details)
- o3 on Aider Polyglot: 81.3% → 76.9%. (details)
- Gemini 3 Pro on ARC-AGI-2: 54% → 31.1%. (details)
- Qwen3.7 (max) on Design Arena Agentic: 1174 → 1179. (details)
- Gemini 3.1 Pro on Design Arena Agentic: 1083 → 1088. (details)
- Kimi K2.5 (thinking) on Design Arena Agentic: 1111 → 1116. (details)
- Qwen3.8 Max (max) on Design Arena Agentic: 1259 → 1264. (details)
- Claude Opus 4.8 on Terminal-Bench 2.1 (Vals): 71.9% → 69.7%. (details)
- Claude Opus 4.8 on SWE-bench (Vals): 88.6% → 85.8%. (details)
- Claude Opus 4.8 on Vibe Code Bench v1.1: 82.7% → 77.5%. (details)
- Claude Opus 4.8 on Design Arena Agentic: 1221 → 1226. (details)
- …and 43 more.
Speed changes
- Claude Fable 5.1 time to first token changed from 2.28 s to 3.74 s. (details)
- Claude Fable 5.1 output speed changed from 39 tok/s to 63 tok/s. (details)
- Muse Wonder output speed changed from 121 tok/s to 70 tok/s. (details)
- Muse Wonder time to first token changed from 6.25 s to 3.36 s. (details)
- Claude Sonnet 5.5 time to first token changed from 1.00 s to 1.49 s. (details)
- GPT-5.5 time to first token changed from 2.09 s to 3.08 s. (details)
- Claude Opus 4.7 time to first token changed from 0.73 s to 1.07 s. (details)
- GPT-5.3-Codex time to first token changed from 1.31 s to 2.42 s. (details)
- Muse Spark 1.1 time to first token changed from 0.50 s to 1.81 s. (details)
- Muse Spark 1.3 time to first token changed from 1.69 s to 2.92 s. (details)
- Muse Spark 1.2 time to first token changed from 2.19 s to 2.97 s. (details)
- GLM 5.2 time to first token changed from 0.51 s to 0.89 s. (details)
- Grok 4.20 Multi-Agent output speed changed from 498 tok/s to 316 tok/s. (details)
- Grok 4.20 Multi-Agent time to first token changed from 3.00 s to 16.72 s. (details)
- Claude Sonnet 4.5 time to first token changed from 1.49 s to 0.94 s. (details)
- …and 63 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.