Gemini 4 Carbon + 3 new AI models: 26 Oct–1 Nov
4 new models incl. Gemini 4 Carbon, GPT-6.1 Terra and Mistral Large 4.0.8, Mistral Small 3.1 up 2.9, 69 price cuts, 1329 new benchmark results: what moved on the BenchLeader Index this week.
The week of 26 Oct 2026 to 1 Nov 2026, from 7 daily updates.
Three things that happened
- Biggest riser: Mistral Small 3.1, up 2.9 points to 38.5 on the BenchLeader Index as new results landed.
- 4 new models arrived: Mistral Large 4.0.8, Gemini 4 Carbon, Mistral Large 4 OSS, GPT-6.1 Terra.
- Busiest benchmark: AA Progress Index v1 with 632 new results; 1329 new results were published in all.
Index movers
- Command A+-6.9
- Granite 4.2 3B-6.7
- Mistral Small 4-6.3
- Muse Spark Open-5.8
- MiniMax M3.1 Flash-5.3
- Gemini 3.5 Flash Lite-4.5
- Inkling-4.2
- Qwen3.8 2.4T A95B-4.1
| Model | Provider | 26 Oct 2026 | 1 Nov 2026 | Change | |---|---|---:|---:|---:| | Command A+ | Cohere | 52.6 | 45.7 | -6.9 | | Granite 4.2 3B | IBM | 45.9 | 39.2 | -6.7 | | Mistral Small 4 | Mistral AI | 46.5 | 40.2 | -6.3 | | Muse Spark Open | Meta | 59.5 | 53.7 | -5.8 | | MiniMax M3.1 Flash | MiniMax | 57.4 | 52.1 | -5.3 | | Gemini 3.5 Flash Lite | Google | 56.0 | 51.5 | -4.5 | | Inkling | Thinking Machines | 54.4 | 50.2 | -4.2 | | Qwen3.8 2.4T A95B | Alibaba | 56.1 | 52.0 | -4.1 | | Granite 4.2 30B | IBM | 50.0 | 45.9 | -4.1 | | GLM 5.3 Flash | Zhipu AI | 60.7 | 56.7 | -4.0 |
New models
- Mistral Large 4.0.8 (Mistral AI) is now listed at $1.05/M blended; no independent results yet. (details)
- Gemini 4 Carbon (Google) is now listed; no independent results yet. (details)
- Mistral Large 4 OSS (high) (Mistral AI) is now listed; no independent results yet. (details)
- GPT-6.1 Terra (OpenAI) appeared with 2 benchmark results. (details)
Price changes
- Laguna S 2.1 (no reasoning) input price moved from $0.090/M to $0.00/M (100% down).
- Laguna XS 2.1 input price moved from $0.060/M to $0.00/M (100% down).
- Qwen-MT Plus output price moved from $7.37/M to $0.78/M (89% down).
- Qwen-VL (max) output price moved from $3.20/M to $0.57/M (82% down).
- Qwen-Plus output price moved from $1.20/M to $0.29/M (76% down).
- QwQ Plus output price moved from $2.40/M to $0.57/M (76% down).
- Reka Flash 3 output price moved from $0.80/M to $0.20/M (75% down).
- Qwen3.5 Plus (thinking) output price moved from $2.40/M to $0.69/M (71% down).
- Qwen3.5 Flash input price moved from $0.10/M to $0.029/M (71% down).
- Muse Spark 1.3 (max) cost per task moved from $3.69/M to $1.31/M (64% down).
- Mistral Large 4 (high) cost per task moved from $5.54/M to $2.06/M (63% down).
- Muse Wonder (max) cost per task moved from $8.63/M to $3.27/M (62% down).
- Qwen3 Coder Flash output price moved from $1.50/M to $0.57/M (62% down).
- Qwen3 8B (thinking) input price moved from $0.18/M to $0.072/M (60% down).
- Qwen3 32B output price moved from $2.80/M to $1.15/M (59% down).
Top five as of 13 Nov 2026
- Claude Fable 5.2 — 72.7
- Gemini 4 Carbon — 69.5
- Claude Opus 5.5 — 68.4
- GPT-6 Astra — 67.1
- Claude Fable 5.1 — 66.6
More: New AI model releases this week, and the full LLM leaderboard 2026.
Generated from the week's daily updates; every line links to the page where the numbers and their sources can be checked.
The week in dated, citable sentences: state of the leaderboard, week 44.