Benchmark Almanac

Mana RP Bench

MiMo-V2.6 Pro 1,280 leads since September 2026
Not in model cards

Models write the next turn in a player’s story. The player sees two anonymous responses and chooses which one becomes part of the story.

The maker ranks 38 models from 2,197 player votes. It marks models with fewer than 100 counted votes as provisional.

Made by
Mana
Kind
Creative writing
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Measures
Preference
In and out
Text → Text
Interaction
Multi-agent
Environment
Mana
Refresh
Live
Run by
A host
In views
Games, Agents, Kept fresh
Strongest model tested
Gemini 4 Carbon #3 on the capability index
Last model added
October 2026
Scores refreshed
November 20th, 2026
38
Entries on its own leaderboard, 32 models we track

MiMo-V2.6 Pro leads with 1,280 MiMo-V2.6 Pro leads with 1,280

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

Bars start at 900.

  1. 1 MiMo-V2.6 Pro 1,280
  2. 2 Muse Spark 1.2 Contributor 1,273
  3. 3 Gemini 3.8 Flash 1,273
  4. 4 GLM-5.1 1,264
  5. 5 Kimi K3 1,255
  6. 6 Claude Opus 5 1,253
  7. 7 Aion 3 1,252
  8. 8 Claude Sonnet 4.5 1,245
  9. 9 Kimi K3.1 Pro 1,240
  10. 10 Aion 3 Mini 1,237
  11. 11 Gemini 3.5 Flash 1,231
  12. 12 Gemini 3 Flash 1,227
  13. 13 GLM-5.3-Flash 1,227
  14. 14 GLM-5 1,225
  15. 15 Claude Opus 5.5 1,220
  16. 16 Deepseek v4.1 Flash 0731 1,217
  17. 17 Claude Opus 4.6 1,213
  18. 18 GLM-5.3 1,213
  19. 19 Gemini 3.1 Pro 1,212
  20. 20 Grok 4.20 1,195
  21. 21 GLM-5.2 1,195
  22. 22 MiMo-V2.5-Pro 1,194
  23. 23 LongCat-2.0 1,193
  24. 24 Claude Sonnet 5.5 1,189
  25. 25 DeepSeek V4 Pro 0813 1,188
  26. 26 Claude Sonnet 4.6 1,177
  27. 27 MiniMax-M3 1,172
  28. 28 Gemini 4 Argon 1,169
  29. 29 DeepSeek-V4-Pro 1,165
  30. 30 Aion 2 1,163
  31. 31 DeepSeek V4.1 Flash 1017 1,161
  32. 32 Gemini 4 Carbon 1,160
  33. 33 Grok 4.7 1,158
  34. 34 Muse Wonder 1,139
  35. 35 Muse Spark 1.3 Contributor 1,127
  36. 36 DeepSeek V4 Flash 0731 1,117
  37. 37 Grok 4.6 1,108
  38. 38 Claude Haiku 5.5 993

Source: Official Mana RP Bench leaderboard

Source: Official Mana RP Bench leaderboard

#EntryScore ±SettingDateSource
1 MiMo-V2.6 Pro 1,280 ±67 Sep 2026 Official leaderboard
2 Muse Spark 1.2 Contributor 1,273 ±69 Official leaderboard
3 Gemini 3.8 Flash 1,273 ±67 Sep 2026 Official leaderboard
4 GLM-5.1 1,264 ±63 Apr 2026 Official leaderboard
5 Kimi K3 1,255 ±61 Jul 2026 Official leaderboard
6 Claude Opus 5 1,253 ±58 Jul 2026 Official leaderboard
7 Aion 3 1,252 ±68 Official leaderboard
8 Claude Sonnet 4.5 1,245 ±62 Sep 2025 Official leaderboard
9 Kimi K3.1 Pro 1,240 ±71 Oct 2026 Official leaderboard
10 Aion 3 Mini 1,237 ±65 Official leaderboard
11 Gemini 3.5 Flash 1,231 ±67 May 2026 Official leaderboard
12 Gemini 3 Flash 1,227 ±55 Dec 2025 Official leaderboard
13 GLM-5.3-Flash 1,227 ±69 Aug 2026 Official leaderboard
14 GLM-5 1,225 ±67 Feb 2026 Official leaderboard
15 Claude Opus 5.5 1,220 ±54 Sep 2026 Official leaderboard
16 Deepseek v4.1 Flash 0731 1,217 ±56 Official leaderboard
17 Claude Opus 4.6 1,213 ±52 Feb 2026 Official leaderboard
18 GLM-5.3 1,213 ±50 Aug 2026 Official leaderboard
19 Gemini 3.1 Pro 1,212 ±54 Feb 2026 Official leaderboard
20 Grok 4.20 1,195 ±71 Feb 2026 Official leaderboard
21 GLM-5.2 1,195 ±63 Jun 2026 Official leaderboard
22 MiMo-V2.5-Pro 1,194 ±61 Apr 2026 Official leaderboard
23 LongCat-2.0 1,193 ±61 Jul 2026 Official leaderboard
24 Claude Sonnet 5.5 1,189 ±51 Sep 2026 Official leaderboard
25 DeepSeek V4 Pro 0813 1,188 ±57 Aug 2026 Official leaderboard
26 Claude Sonnet 4.6 1,177 ±62 Feb 2026 Official leaderboard
27 MiniMax-M3 1,172 ±62 Jun 2026 Official leaderboard
28 Gemini 4 Argon 1,169 ±74 Sep 2026 Official leaderboard
29 DeepSeek-V4-Pro 1,165 ±63 Apr 2026 Official leaderboard
30 Aion 2 1,163 ±54 Official leaderboard
31 DeepSeek V4.1 Flash 1017 1,161 ±75 Oct 2026 Official leaderboard
32 Gemini 4 Carbon 1,160 ±76 Oct 2026 Official leaderboard
33 Grok 4.7 1,158 ±63 Sep 2026 Official leaderboard
34 Muse Wonder 1,139 ±70 Oct 2026 Official leaderboard
35 Muse Spark 1.3 Contributor 1,127 ±66 Official leaderboard
36 DeepSeek V4 Flash 0731 1,117 ±63 Jul 2026 Official leaderboard
37 Grok 4.6 1,108 ±71 Aug 2026 Official leaderboard
38 Claude Haiku 5.5 993 ±93 Oct 2026 Official leaderboard
#ModelScore ±SettingDateSource
1 MiMo-V2.6 Pro 1,280 ±67 Sep 2026 Official leaderboard
2 Gemini 3.8 Flash 1,273 ±67 Sep 2026 Official leaderboard
3 GLM-5.1 1,264 ±63 Apr 2026 Official leaderboard
4 Kimi K3 1,255 ±61 Jul 2026 Official leaderboard
5 Claude Opus 5 1,253 ±58 Jul 2026 Official leaderboard
6 Claude Sonnet 4.5 1,245 ±62 Sep 2025 Official leaderboard
7 Kimi K3.1 Pro 1,240 ±71 Oct 2026 Official leaderboard
8 Gemini 3.5 Flash 1,231 ±67 May 2026 Official leaderboard
9 Gemini 3 Flash 1,227 ±55 Dec 2025 Official leaderboard
10 GLM-5.3-Flash 1,227 ±69 Aug 2026 Official leaderboard
11 GLM-5 1,225 ±67 Feb 2026 Official leaderboard
12 Claude Opus 5.5 1,220 ±54 Sep 2026 Official leaderboard
13 Claude Opus 4.6 1,213 ±52 Feb 2026 Official leaderboard
14 GLM-5.3 1,213 ±50 Aug 2026 Official leaderboard
15 Gemini 3.1 Pro 1,212 ±54 Feb 2026 Official leaderboard
16 Grok 4.20 1,195 ±71 Feb 2026 Official leaderboard
17 GLM-5.2 1,195 ±63 Jun 2026 Official leaderboard
18 MiMo-V2.5-Pro 1,194 ±61 Apr 2026 Official leaderboard
19 LongCat-2.0 1,193 ±61 Jul 2026 Official leaderboard
20 Claude Sonnet 5.5 1,189 ±51 Sep 2026 Official leaderboard
21 DeepSeek V4 Pro 0813 1,188 ±57 Aug 2026 Official leaderboard
22 Claude Sonnet 4.6 1,177 ±62 Feb 2026 Official leaderboard
23 MiniMax-M3 1,172 ±62 Jun 2026 Official leaderboard
24 Gemini 4 Argon 1,169 ±74 Sep 2026 Official leaderboard
25 DeepSeek-V4-Pro 1,165 ±63 Apr 2026 Official leaderboard
26 DeepSeek V4.1 Flash 1017 1,161 ±75 Oct 2026 Official leaderboard
27 Gemini 4 Carbon 1,160 ±76 Oct 2026 Official leaderboard
28 Grok 4.7 1,158 ±63 Sep 2026 Official leaderboard
29 Muse Wonder 1,139 ±70 Oct 2026 Official leaderboard
30 DeepSeek V4 Flash 0731 1,117 ±63 Jul 2026 Official leaderboard
31 Grok 4.6 1,108 ±71 Aug 2026 Official leaderboard
32 Claude Haiku 5.5 993 ±93 Oct 2026 Official leaderboard

4 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic Z.ai Google DeepMind Xiaomi Corp
Own leaderboard 4 leaders

Source: Official Mana RP Bench leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
900 1,000 1,100 1,200 1,300 2026 2027 900 1,000 1,100 1,200 1,300 2026 2027

Source: Official Mana RP Bench leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Writing and taste

All 65 in Writing and taste
  • Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
  • WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
  • Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing. MiniMax-Text-01 81.3%
  • DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate. DeepSeek-V4-Pro 62.6%
  • Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
  • Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right. Muse Spark 0.21

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (38 entries).
  • Pass Models scored 32 models we track, plus 6 other entries on its leaderboard.
  • Pass Newest score The newest is from October 2026, for Gemini 4 Carbon.
  • Pass Frontier models 4 of the top 10 have a score, led by Gemini 4 Carbon (#3).
  • Note Headroom Scored as an Elo rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on mana.land: 32 rows for models we track and 6 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check