State of the leaderboard: week 41, 5–11 October 2026
Complete week: data as of , from 7 daily updates
The week in 6 sentences
- In week 41 of 2026 (5–11 October 2026), Claude Opus 5.5 (Anthropic) held the #1 spot on the BenchLeader Index at 69.5, 0.8 points ahead of Claude Fable 5.1 (68.7).
- 2 models entered the top 10 (Claude Sonnet 5.5 at #9 and Muse Spark 1.3 at #10), pushing out GPT-5.5 and Muse Spark; 4 other models changed places.
- 4 new models arrived; the highest-ranked is Claude Haiku 5.5 (Anthropic) at #78 with an index of 57.5.
- The biggest riser was Claude Sonnet 5.5, up 1.5 points to 65.1; the biggest faller GPT-6 Luna, down 1.4 to 57.8.
- 6 models cut a list price and 7 models raised one; the largest cut was Qwen-VL OCR's input price, 90% lower.
- 620 new benchmark results were published, the most on PRBench Finance (70).
Top 10 at the end of the week
The BenchLeader Index, one row per model at its best reasoning effort, against the table at the end of the previous week. Left the top 10: GPT-5.5, Muse Spark.
| # | Model | Provider | Index | Last week | Move |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 69.5 | 1 | – |
| 2 | Claude Fable 5.1 | Anthropic | 68.7 | 3 | ↑1 |
| 3 | GPT-6 Astra | OpenAI | 68.5 | 2 | ↓1 |
| 4 | Claude Fable 5 | Anthropic | 67.8 | 5 | ↑1 |
| 5 | GPT-6.1 Sol | OpenAI | 67.6 | 4 | ↓1 |
| 6 | Claude Opus 5 | Anthropic | 66.7 | 6 | – |
| 7 | Gemini 4 Argon | 66.6 | 7 | – | |
| 8 | GPT-5.6 Sol | OpenAI | 65.8 | 8 | – |
| 9 | Claude Sonnet 5.5 | Anthropic | 65.1 | – | new |
| 10 | Muse Spark 1.3 | Meta | 65.0 | – | new |
New models and their first results
- Nano Banana 2.1 (Google): not enough independent results for an index yet
- Claude Haiku 5.5 (Anthropic): #78 on the index at 57.5. First results: 33.7% on AutomationBench; 17.2% on GDP.pdf (AA); 1.1% on Harvey LAB-AA v1.1; 1442 on AA-Briefcase v1.1.
- GPT-6 Sol (Daybreak Blue, max) (OpenAI): not enough independent results for an index yet
- Ling 3.0 Flash Sante (Ant Group): not enough independent results for an index yet
Biggest movers on the index
| Model | Provider | 5 Oct 2026 | 11 Oct 2026 | Change |
|---|---|---|---|---|
| Claude Sonnet 5.5 | Anthropic | 63.6 | 65.1 | +1.5 |
| GPT-6 Luna | OpenAI | 59.2 | 57.8 | -1.4 |
| Grok 4.7 | SpaceXAI | 59.7 | 58.6 | -1.1 |
| Step 5 Preview | StepFun | 59.0 | 59.9 | +0.9 |
| Claude Fable 5.1 | Anthropic | 67.9 | 68.7 | +0.8 |
| GPT-6 Sol | OpenAI | 64.9 | 64.1 | -0.8 |
| Qwen3.8 Max | Alibaba | 63.8 | 63.0 | -0.8 |
| Llama 4 Maverick | Meta | 43.9 | 43.2 | -0.7 |
| MiMo-V2.6-Flash | Xiaomi | 58.1 | 58.7 | +0.6 |
| GPT-4o | OpenAI | 45.1 | 44.5 | -0.6 |
Price changes
Cheaper (6)
- Qwen-VL OCR input price moved from $0.72/M to $0.070/M (90% down).
- GPT-5.6 Sol Pro (max) input price moved from $4.00/M to $2.00/M (50% 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 $0.060/M to $0.050/M (17% down).
- Qwen3.8 27B input price moved from $0.45/M to $0.42/M (6% down).
More expensive (7)
- Nano Banana 2.1 output price moved from $7.50/M to $30.00/M (300% up).
- LongCat 2.0 input price moved from $0.30/M to $0.75/M (150% up).
- Ling 3.0 Flash Sante input price moved from $0.042/M to $0.075/M (79% up).
- Nemotron 3 Nano Omni 30B A3b (thinking) input price moved from $0.20/M to $0.30/M (50% up).
- Nemotron 3 Nano 30B A3B input price moved from $0.050/M to $0.060/M (20% up).
- DeepSeek V4 Flash (high) input price moved from $0.11/M to $0.13/M (18% up).
- Gemma 4 31B (no reasoning) input price moved from $0.14/M to $0.15/M (7% up).
List prices per million tokens; each model's full price history is on its page and the LLM API pricing tracker.
Other weeks
← Week 42, 12–18 Oct 2026 · Week 40, 28 Sep–4 Oct 2026 → · The weekly review on the blog
- Week 45, 2–8 Nov 2026
- Week 44, 26 Oct–1 Nov 2026
- Week 43, 19–25 Oct 2026
- Week 42, 12–18 Oct 2026
- Week 41, 5–11 Oct 2026
- Week 40, 28 Sep–4 Oct 2026
- Week 39, 21–27 Sep 2026
- Week 38, 14–20 Sep 2026
- Week 37, 7–13 Sep 2026
Benchmark categories: AI agent benchmarks · AI coding benchmarks · Reasoning and math benchmarks · Multimodal AI benchmarks · New AI model releases
How this is built: the BenchLeader Index is recomputed with every update from independent benchmark publishers (see the methodology), and a maker's own launch numbers are never used. Past ranks are rebuilt from the daily index history of the models listed today.
Cite as: BenchLeader, “AI leaderboard week 41, 5–11 Oct 2026: who was #1”, data as of 11 Oct 2026, https://www.benchleader.com/state/2026-w41.