Kimi K3.1 Pro + 9 new AI models: 19 Oct–25 Oct
10 new models incl. Kimi K3.1 Pro, MiniMax M3.1 Flash and Nemotron 3.5 Bolt E4B 4GB, Gemini 1.5 Pro up 3.7, 70 price cuts, 1149 new benchmark results: what moved on the BenchLeader Index this week.
The week of 19 Oct 2026 to 25 Oct 2026, from 7 daily updates.
Three things that happened
- Biggest riser: Gemini 1.5 Pro, up 3.7 points to 46.1 on the BenchLeader Index as new results landed.
- 10 new models arrived: Kimi K3.1 Pro, Nemotron 3.5 Bolt E4B 4GB, Nemotron Super VL 3.5 NVFP4, Smaug Nemotron 3.5 NVFP4, Spark X2.6 and more.
- Busiest benchmark: MLCR with 98 new results; 1149 new results were published in all.
Index movers
- Gemini 1.5 Pro+3.7
- Beam 1.0-3.4
- Nemotron 3.5 Super VL 120B A12B-3.3
- DeepSeek V3.1-3.1
- Gemini 1.5 Pro 002-3.0
- Granite 4.0 Nano 1B-3.0
- Magistral Medium+2.4
- Qwen3.8 2.4T A95B-2.2
| Model | Provider | 19 Oct 2026 | 25 Oct 2026 | Change | |---|---|---:|---:|---:| | Gemini 1.5 Pro | Google | 42.4 | 46.1 | +3.7 | | Beam 1.0 | Reflection | 54.6 | 51.2 | -3.4 | | Nemotron 3.5 Super VL 120B A12B | NVIDIA | 53.7 | 50.4 | -3.3 | | DeepSeek V3.1 | DeepSeek | 51.2 | 48.1 | -3.1 | | Gemini 1.5 Pro 002 | Google | 44.6 | 41.6 | -3.0 | | Granite 4.0 Nano 1B | IBM | 37.4 | 34.4 | -3.0 | | Magistral Medium | Mistral AI | 39.4 | 41.8 | +2.4 | | Qwen3.8 2.4T A95B | Alibaba | 63.2 | 61.0 | -2.2 | | Gemini 1.5 Flash 002 | Google | 40.5 | 38.3 | -2.2 | | Muse Wonder Full | Meta | 68.6 | 70.6 | +2.0 |
New models
- Kimi K3.1 Pro (Moonshot AI) appeared with 6 benchmark results, entering the BenchLeader Index at #37. (details)
- Nemotron 3.5 Bolt E4B 4GB (thinking) (NVIDIA) appeared with 1 benchmark result. (details)
- Nemotron Super VL 3.5 NVFP4 (NVIDIA) appeared with 1 benchmark result. (details)
- Smaug Nemotron 3.5 NVFP4 (NVIDIA) appeared with 1 benchmark result. (details)
- Spark X2.6 (Synlan) appeared with 1 benchmark result. (details)
- Kimi K3.1 Pro Highspeed (Moonshot AI) is now listed at $8.00/M blended; no independent results yet. (details)
- Qwen3.8 Max Internal (Alibaba) is now listed; no independent results yet. (details)
- GPT-5.6 Sol Keenable (max) (OpenAI) is now listed; no independent results yet. (details)
- MiniMax-M3.1-Flash (MiniMax) appeared with 5 benchmark results, entering the BenchLeader Index at #85. (details)
- Mercury 3 (Inception) is now listed at $0.16/M blended; no independent results yet. (details)
Price changes
- Qwen-MT Plus output price moved from $7.37/M to $0.78/M (89% down).
- Qwen2.5 VL 72B Instruct output price moved from $8.40/M to $1.00/M (88% down).
- Muse Spark Open (xhigh) cached input price moved from $1.25/M to $0.15/M (88% down).
- Qwen3-Omni Flash input price moved from $0.43/M to $0.06/M (87% down).
- Qwen-VL (max) output price moved from $3.20/M to $0.57/M (82% down).
- Quasar 438B (max) input price moved from $0.60/M to $0.11/M (82% down).
- Mistral Nemo input price moved from $0.15/M to $0.029/M (81% down).
- Nemotron 3 Super 120B A12B (thinking) cached input price moved from $0.30/M to $0.060/M (80% down).
- Nemotron 3.5 Super VL cached input price moved from $0.30/M to $0.060/M (80% down).
- Qwen2.5 7B Instruct output price moved from $0.70/M to $0.14/M (79% 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).
- 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).
- Qwen2.5 32B Instruct output price moved from $2.80/M to $0.86/M (69% down).
Top five as of 25 Oct 2026
- Claude Opus 5.5 — 72.6
- Gemini 4 Argon — 70.7
- Muse Wonder Full — 70.6
- Claude Fable 5.1 — 70.5
- GPT-6 Astra — 70.4
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.