State of the leaderboard: week 45, 2–8 November 2026
Complete week: data as of , from 7 daily updates
The week in 6 sentences
- In week 45 of 2026 (2–8 November 2026), Claude Opus 5.5 (Anthropic) held the #1 spot on the BenchLeader Index at 69.4, 0.1 points ahead of Gemini 4 Carbon (69.3).
- 1 model entered the top 10 (Claude Sonnet 5.5 at #10), pushing out GPT-6.1 Terra; 4 other models changed places.
- 12 new models arrived; the highest-ranked is Kimi K3.1 Pro Together (Moonshot AI) at #37 with an index of 60.5.
- The biggest riser was DeepSeek V3.1, up 3.5 points to 52.5; the biggest faller DeepSeek V3 0324, down 6.4 to 47.0.
- 16 models cut a list price and 38 models raised one; the largest cut was Nemotron 3 Super 120B A12B's output price, 63% lower.
- 314 new benchmark results were published, the most on Arena Search (22).
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-6.1 Terra.
| # | Model | Provider | Index | Last week | Move |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 69.4 | 1 | – |
| 2 | Gemini 4 Carbon | 69.3 | 2 | – | |
| 3 | GPT-6 Astra | OpenAI | 68.3 | 3 | – |
| 4 | Claude Fable 5.1 | Anthropic | 67.3 | 5 | ↑1 |
| 5 | GPT-6.1 Sol | OpenAI | 67.3 | 4 | ↓1 |
| 6 | Claude Fable 5 | Anthropic | 66.6 | 6 | – |
| 7 | Gemini 4 Argon | 66.1 | 7 | – | |
| 8 | GPT-5.6 Sol | OpenAI | 65.5 | 9 | ↑1 |
| 9 | Claude Opus 5 | Anthropic | 65.4 | 8 | ↓1 |
| 10 | Claude Sonnet 5.5 | Anthropic | 65.4 | – | new |
New models and their first results
- Nanbeige4.3-33B (Nanbeige): not enough independent results for an index yet
- GLM 5.3 FlashX Legal (Zhipu AI): not enough independent results for an index yet
- Mistral Large 4.0 OSS (Mistral AI): #176 on the index at 50.0
- crouton-alpha: not enough independent results for an index yet
- Gemini Omni 1.1 Flash (Google): not enough independent results for an index yet
- Gemini Omni 1.2 Flash (Google): not enough independent results for an index yet
- Ripple-65B Preview (Ricursive): not enough independent results for an index yet
- Kimi K3.1 Pro Together (Moonshot AI): #37 on the index at 60.5
- Inkling 2 Small (Thinking Machines): #66 on the index at 58.4. First results: 1648 on Arena WebDev.
- lfm-3-1-7b: not enough independent results for an index yet
- LFM2.5-24B-A2B (Liquid AI): not enough independent results for an index yet
- LFM3-1.7B (Liquid AI): not enough independent results for an index yet
Biggest movers on the index
| Model | Provider | 2 Nov 2026 | 8 Nov 2026 | Change |
|---|---|---|---|---|
| DeepSeek V3 0324 | DeepSeek | 53.4 | 47.0 | -6.4 |
| North Mini Code | Cohere | 46.6 | 40.2 | -6.4 |
| DeepSeek V3.1 | DeepSeek | 49.0 | 52.5 | +3.5 |
| Solar Pro 4 | Upstage | 52.0 | 49.7 | -2.3 |
| MiniMax M3.1 Flash | MiniMax | 52.1 | 54.3 | +2.2 |
| Gemini 3.1 Flash Lite | 54.3 | 52.5 | -1.8 | |
| MiMo-V2.5 | Xiaomi | 55.1 | 56.4 | +1.3 |
| Inkling 2 Small | Thinking Machines | 57.5 | 58.4 | +0.9 |
| Mistral Medium 3.5 | Mistral AI | 47.3 | 46.6 | -0.7 |
| GLM 5.2 | Zhipu AI | 60.1 | 59.5 | -0.6 |
Price changes
Cheaper (16)
- Nemotron 3 Super 120B A12B output price moved from $2.40/M to $0.90/M (63% down).
- GLM 4.5V input price moved from $0.60/M to $0.30/M (50% down).
- GLM 4.6V output price moved from $0.90/M to $0.45/M (50% down).
- GLM-5 input price moved from $1.00/M to $0.60/M (40% down).
- GLM 5V Turbo input price moved from $1.20/M to $0.75/M (38% down).
- GLM 5.1 input price moved from $1.40/M to $0.90/M (36% down).
- DeepSeek V4.1 Flash 1017 (no reasoning) input price moved from $0.45/M to $0.30/M (33% down).
- DeepSeek V3.1 (thinking) input price moved from $0.58/M to $0.43/M (26% down).
- GLM 4.7 input price moved from $0.60/M to $0.45/M (25% down).
- GLM 5.3 FlashX (low) input price moved from $0.37/M to $0.30/M (19% down).
- MiMo-V2.5-Pro (thinking) output price moved from $1.02/M to $0.87/M (15% down).
- GLM 5.2 input price moved from $1.40/M to $1.20/M (15% down).
- …and 4 more.
More expensive (38)
- Qwen-MT Plus output price moved from $0.78/M to $7.37/M (851% up).
- Qwen-VL (max) output price moved from $0.57/M to $3.20/M (457% up).
- Qwen-Plus output price moved from $0.29/M to $1.20/M (318% up).
- QwQ Plus output price moved from $0.57/M to $2.40/M (318% up).
- Qwen3.5 Plus (thinking) output price moved from $0.69/M to $2.40/M (249% up).
- Qwen3.5 Flash input price moved from $0.029/M to $0.10/M (245% up).
- Qwen3 Coder Flash output price moved from $0.57/M to $1.50/M (161% up).
- Qwen3 8B (thinking) input price moved from $0.072/M to $0.18/M (150% up).
- Qwen3 32B output price moved from $1.15/M to $2.80/M (144% up).
- Qwen3 235B A22B output price moved from $1.15/M to $2.80/M (144% up).
- Qwen3 14B output price moved from $0.57/M to $1.40/M (144% up).
- Qwen Turbo output price moved from $0.087/M to $0.20/M (130% up).
- …and 26 more.
List prices per million tokens; each model's full price history is on its page and the LLM API pricing tracker.
Other weeks
← This week · Week 44, 26 Oct–1 Nov 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 45, 2–8 Nov 2026: who was #1”, data as of 8 Nov 2026, https://www.benchleader.com/state/2026-w45.