Benchmarks
Fictionlivebench
Models scored
42
Best score
1
Metric
120k token score
Fictionlivebench is an AI evaluation tracked by Epoch AI, with 42 scored model versions on record. The scores here are reported by third parties rather than produced by Epoch AI running the evaluation itself.
Scored models span December 2024 to January 2026. The best score recorded is 1, measured as 120k token score. Models come from Meta AI, Alibaba, Anthropic, DeepSeek, Google DeepMind,Google, Google DeepMind, OpenAI, xAI and others.
Full record
- Score metric
- 120k token score
- Models scored
- 42
- Best score recorded
- 1
- Earliest model scored
- Dec 17, 2024
- Most recent model scored
- Jan 27, 2026
- Third-party reported
- Yes
Leaderboard
| 01 | o3-2025-04-16_medium | OpenAI | 1 |
| 02 | grok-4-0709 | xAI | 0.97 |
| 03 | gpt-5-2025-08-07_medium | OpenAI | 0.97 |
| 04 | gemini-2.5-pro-exp-03-25 | Google DeepMind | 0.91 |
| 05 | o3-pro-2025-06-10_medium | OpenAI | 0.89 |
| 06 | gemini-2.5-pro-preview-06-05 | Google DeepMind | 0.88 |
| 07 | kimi-k2.5 | Moonshot | 0.78 |
| 08 | grok-4-fast | xAI | 0.75 |
| 09 | gemini-2.5-pro-preview-05-06 | Google DeepMind | 0.72 |
| 10 | gemini-2.5-pro-preview-03-25 | Google DeepMind | 0.72 |
| 11 | chutes/Qwen3-235B-A22B-Thinking-2507 | Alibaba | 0.69 |
| 12 | gemini-2.5-flash-preview-05-20 | Google DeepMind | 0.69 |
| 13 | grok-3-mini-beta_medium | xAI | 0.66 |
| 14 | chatgpt-4o-01-29-2025 | OpenAI | 0.66 |
| 15 | gpt-4.5-preview-2025-02-27 | OpenAI | 0.64 |
| 16 | gpt-4.1-2025-04-14 | OpenAI | 0.63 |
| 17 | gemini-2.0-flash-001 | Google DeepMind,Google | 0.63 |
| 18 | o4-mini-2025-04-16_medium | OpenAI | 0.63 |
| 19 | gpt-5-mini-2025-08-07_medium | OpenAI | 0.63 |
| 20 | deepinfra/Qwen3-Next-80B-A3B-Instruct | 0.63 | |
| 21 | MiniMax-M1-80k | MiniMax | 0.59 |
| 22 | grok-3-beta | xAI | 0.58 |
| 23 | claude-3-7-sonnet-20250219_8K | Anthropic | 0.53 |
| 24 | gemini-2.5-flash-preview-04-17 | Google DeepMind | 0.53 |
| 25 | o1-2024-12-17_medium | OpenAI | 0.53 |
| 26 | DeepSeek-V3.1 | DeepSeek | 0.53 |
| 27 | chutes/Qwen3-Next-80B-A3B-Instruct | 0.47 | |
| 28 | gpt-4.1-mini-2025-04-14 | OpenAI | 0.47 |
| 29 | parasail-qwen3-235b-a22b-instruct-2507 | Alibaba | 0.44 |
| 30 | o3-mini-2025-01-31_medium | OpenAI | 0.44 |
| 31 | fireworks/Kimi-K2-Instruct-0905 | Moonshot | 0.41 |
| 32 | claude-opus-4-20250514 | Anthropic | 0.38 |
| 33 | gemini-2.0-pro-exp-02-05 | Google DeepMind | 0.38 |
| 34 | gemini-2.0-flash-thinking-exp-01-21 | Google DeepMind,Google | 0.38 |
| 35 | chutes/Llama-4-Maverick-17B-128E-Instruct | Meta AI | 0.36 |
| 36 | claude-sonnet-4-20250514 | Anthropic | 0.36 |
| 37 | claude-3-7-sonnet-20250219 | Anthropic | 0.34 |
| 38 | DeepSeek-R1 | DeepSeek | 0.33 |
| 39 | chutes/Llama-4-Scout-17B-16E Instruct | Meta AI | 0.27 |
| 40 | gemini-2.5-flash-lite-preview-06-17-thinking | Google DeepMind | 0.22 |
| 41 | gpt-5-nano-2025-08-07_medium | OpenAI | 0.22 |
| 42 | gpt-4.1-nano-2025-04-14 | OpenAI | 0.19 |
More benchmarks
SourceEpoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/benchmarks. Licensed under CC BY 4.0.
← All benchmarks