The week on the leaderboard, 5 Oct 2026 to 11 Oct 2026
Claude Sonnet 5.5 up 5.8, 4 new models, 13 price cuts, 620 new benchmark results. What moved on the BenchLeader Index this week and why.
The week of 5 Oct 2026 to 11 Oct 2026, from 7 daily updates.
Three things that happened
- Biggest riser: Claude Sonnet 5.5, up 5.8 points to 67.6 on the BenchLeader Index as new results landed.
- 4 new models arrived: GPT-6 Sol (Daybreak Blue, max), Ling 3.0 Flash Sante, Claude Haiku 5.5, Nano Banana 2.1.
- Busiest benchmark: PRBench Finance with 70 new results; 620 new results were published in all.
Index movers
- Claude Sonnet 5.5+5.8
- Claude Fable 5+4.6
- Claude Fable 5.1+2.4
- Claude Opus 5.5+2.0
- Qwen3.8 Max-0.8
- Step 5 Preview+0.8
- GPT-6 Sol-0.7
- Grok 4.7+0.7
| Model | Provider | 5 Oct 2026 | 11 Oct 2026 | Change | |---|---|---:|---:|---:| | Claude Sonnet 5.5 | Anthropic | 61.8 | 67.6 | +5.8 | | Claude Fable 5 | Anthropic | 64.5 | 69.1 | +4.6 | | Claude Fable 5.1 | Anthropic | 68.4 | 70.8 | +2.4 | | Claude Opus 5.5 | Anthropic | 70.0 | 72.0 | +2.0 | | Qwen3.8 Max | Alibaba | 65.0 | 64.2 | -0.8 | | Step 5 Preview | StepFun | 61.6 | 62.4 | +0.8 | | GPT-6 Sol | OpenAI | 66.3 | 65.6 | -0.7 | | Grok 4.7 | SpaceXAI | 63.6 | 64.3 | +0.7 | | Claude Haiku 5.5 | Anthropic | 60.7 | 61.3 | +0.6 | | Mistral Large 4 | Mistral AI | 58.4 | 57.8 | -0.6 |
New models
- GPT-6 Sol (Daybreak Blue, max) (max) (OpenAI) is now listed at $4.00/M blended; no independent results yet. (details)
- Ling 3.0 Flash Sante (Ant Group) is now listed at $0.06/M blended; no independent results yet. (details)
- Claude Haiku 5.5 (high) (Anthropic) appeared with 4 benchmark results. (details)
- Gemini Nano Banana 2.1 (Google) is now listed at $3.00/M blended; no independent results yet. (details)
Price changes
- Claude Sonnet 5.5 (low) cost per task moved from 7.7 to 0.3 (95% down).
- Claude Opus 5.5 (low) cost per task moved from 6 to 0.6 (91% down).
- Qwen-VL OCR input price moved from $0.72/M to $0.07/M (90% down).
- Claude Fable 5.1 (low) cost per task moved from 7.6 to 2.4 (69% down).
- MiniMax-M2.5-highspeed cached input price moved from $0.06/M to $0.03/M (50% down).
- GPT-5.6 Sol Pro (max) input price moved from $4.00/M to $2.00/M (50% down).
- Grok 4.6 (xhigh) cost per task moved from 2.3 to 1.8 (25% down).
- Muse Glimmer output price moved from $1.50/M to $1.20/M (20% down).
- Nemotron 3 Nano Omni 30B A3b (thinking) output price moved from $1.10/M to $0.90/M (18% down).
- Nemotron 3 Nano 30B A3B input price moved from $0.06/M to $0.05/M (17% down).
- Grok 4.5 (high) cost per task moved from 1 to 0.9 (15% down).
- DeepSeek V4 Flash 0731 (high) cached input price moved from $0.03/M to $0.03/M (7% down).
- Qwen3.8 27B input price moved from $0.45/M to $0.42/M (6% down).
- LongCat 2.0 output price moved from $1.20/M to $2.95/M (146% up).
- BGE M3 input price moved from $0.00/M to $0.01/M (1000000000% up).
Top five as of 11 Oct 2026
- Claude Opus 5.5 — 72.0
- Claude Fable 5.1 — 70.8
- GPT-6 Astra — 70.2
- Claude Opus 5.5 — 70.2
- Gemini 4 Argon — 70.0
Generated from the week's daily updates; every line links to the page where the numbers and their sources can be checked.