Benchmark Almanac

Genspark Slides Benchmark

Claude Fable 5.1 83.6% leads since September 2026
Not in model cards

Models build finished slide decks from 200 real production tasks in the Genspark Slides agent harness. An internal grader scores quality, completion, content and design.

11 models in the Fireworks index. The maker blog blocks scripted reads.

Made by
Genspark
Kind
Documents and spreadsheets
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
Kept private
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
September 2026
Scores refreshed
November 12th, 2026
11
Entries on its own leaderboard, 10 models we track

Claude Fable 5.1 leads with 83.6% among models released by September 2026

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 83.6 Claude Fable 5.1
  2. 82.2 Gen-1 Slides
  3. 81.0 Claude Opus 5
  4. 79.9 Claude Fable 5
  5. 78.0 GPT-6 Astra
  6. 72.6 Kimi K3
  7. 67.0 GPT-5.6 Sol
  8. 56.1 MiniMax-M3
  9. 54.1 GPT-5.6 Luna
  10. 53.4 Gemini 3.8 Flash
  11. 48.8 GPT-5.6 Terra
  1. 1 Claude Fable 5.1 83.6%
  2. 2 Gen-1 Slides 82.2%
  3. 3 Claude Opus 5 81%
  4. 4 Claude Fable 5 79.9%
  5. 5 GPT-6 Astra 78%
  6. 6 Kimi K3 72.6%
  7. 7 GPT-5.6 Sol 67%
  8. 8 MiniMax-M3 56.1%
  9. 9 GPT-5.6 Luna 54.1%
  10. 10 Gemini 3.8 Flash 53.4%
  11. 11 GPT-5.6 Terra 48.8%

Source: Official Genspark Slides Benchmark leaderboard

#EntryScoreSettingDateSource
1 Claude Fable 5.1 83.6% Sep 2026 Official leaderboard
2 Gen-1 Slides 82.2% Oct 2026 Official leaderboard
3 Claude Opus 5 81% Jul 2026 Official leaderboard
4 Claude Fable 5 79.9% Jun 2026 Official leaderboard
5 GPT-6 Astra 78% Sep 2026 Official leaderboard
6 Kimi K3 72.6% Jul 2026 Official leaderboard
7 GPT-5.6 Sol 67% Jul 2026 Official leaderboard
8 MiniMax-M3 56.1% Jun 2026 Official leaderboard
9 GPT-5.6 Luna 54.1% Jul 2026 Official leaderboard
10 Gemini 3.8 Flash 53.4% Sep 2026 Official leaderboard
11 GPT-5.6 Terra 48.8% Jul 2026 Official leaderboard

Score vs. cost per task

The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.

60% 80% 100% $0$2$4$6$8 Cost per task ($), lower is better Score Claude Fable 5: Score 79.9%, cost per task $6.38 GPT-5.6 Sol: Score 67%, cost per task $2.01 GPT-5.6 Terra: Score 48.8%, cost per task $0.78 Kimi K3: Score 72.6%, cost per task $2 Claude Opus 5: Score 81%, cost per task $4.53 Gemini 3.8 Flash: Score 53.4%, cost per task $0.85 GPT-6 Astra: Score 78%, cost per task $5.17 MiniMax-M3: Score 56.1%, cost per task $0.34 GPT-5.6 Luna: Score 54.1%, cost per task $0.13 Claude Fable 5.1: Score 83.6%, cost per task $5.41 Gen-1 Slides: Score 82.2%, cost per task $0.44. Not in our model list Claude Fable 5.1Gen-1 SlidesMiniMax-M3GPT-5.6 Luna 60% 80% 100% $0$2$4$6$8 Cost per task ($), lower is better Score Claude Fable 5: Score 79.9%, cost per task $6.38 GPT-5.6 Sol: Score 67%, cost per task $2.01 GPT-5.6 Terra: Score 48.8%, cost per task $0.78 Kimi K3: Score 72.6%, cost per task $2 Claude Opus 5: Score 81%, cost per task $4.53 Gemini 3.8 Flash: Score 53.4%, cost per task $0.85 GPT-6 Astra: Score 78%, cost per task $5.17 MiniMax-M3: Score 56.1%, cost per task $0.34 GPT-5.6 Luna: Score 54.1%, cost per task $0.13 Claude Fable 5.1: Score 83.6%, cost per task $5.41 Gen-1 Slides: Score 82.2%, cost per task $0.44. Not in our model list Claude Fable 5.1Gen-1 SlidesMiniMax-M3GPT-5.6 Luna
ModelSettingScoreCost per task
Claude Fable 5.1 83.6% $5.41
Gen-1 Slides 82.2% $0.44
Claude Opus 5 81% $4.53
Claude Fable 5 79.9% $6.38
GPT-6 Astra 78% $5.17
Kimi K3 72.6% $2
GPT-5.6 Sol 67% $2.01
MiniMax-M3 56.1% $0.34
GPT-5.6 Luna 54.1% $0.13
Gemini 3.8 Flash 53.4% $0.85
GPT-5.6 Terra 48.8% $0.78

The best score, 83.6%, costs $5.41 a task

Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

MiniMax OpenAI Moonshot AI Anthropic Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.10 $0.20 $0.50 $1.00 $2.00 $5.00 $10 Cost per task, log scale Claude Fable 5.1 Kimi K3 MiniMax-M3 GPT-5.6 Luna 0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 Cost per task, log scale Claude Fable 5.1 Kimi K3

Source: Official Genspark Slides Benchmark leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.1 83.6% $5.41
Claude Opus 5 81% $4.53
Claude Fable 5 79.9% $6.38
GPT-6 Astra 78% $5.17
Kimi K3 72.6% $2.00
GPT-5.6 Sol 67% $2.01
MiniMax-M3 56.1% $0.34
GPT-5.6 Luna 54.1% $0.13
Gemini 3.8 Flash 53.4% $0.85
GPT-5.6 Terra 48.8% $0.78

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.

MiniMax Anthropic
Own leaderboard Not tested since Sep 2026
Claude Fable 5.1 83.6%

Source: Official Genspark Slides Benchmark leaderboard

Scores over time

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

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5.1 Claude Fable 5 MiniMax-M3 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5.1 MiniMax-M3

Source: Official Genspark Slides Benchmark leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Economic work

All 97 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
  • OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%