Decodability Assessment Benchmark
Models flag words a child cannot yet sound out in a passage, given the phonics lessons the child has completed. The leaderboard reports adjusted balanced accuracy.
Fab AI scores 32 model configurations on Kiswahili and 30 on English. Its public sample pairs one Kiswahili passage with two learner profiles.
- Made by
- Fab AI
- Released
- September 2026
- Kind
- Language reasoning
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Education, Languages and literature
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- Claude Opus 5 #11 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 20th, 2026
GPT-5.5 leads with 95.9% among models released by July 2026 GPT-5.5 leads with 95.9% among models released by July 2026
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.
The newest model with a score here came out in July 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 12 more
- 95.9 GPT-5.5
- 95.9 Claude Fable 5
- 95.7
Gemini 3.6 Flash
- 95.0 GPT-5.4
- 94.0
Gemini 3.5 Flash
- 92.7 Claude Opus 5
- 92.3 GPT-5.6 Sol
- 90.5
Gemini 3 Flash
- 89.8 GPT-5.6 Terra
- 88.1 Grok 4.5
- 88.0
Gemini 3.1 Pro
- 84.1 GPT-5.6 Luna
- 78.3 Claude Sonnet 5
- 66.2 o3
- 61.3
DeepSeek-V4-Pro
- 55.8 gpt-oss-120b
- 52.9 o4-mini
- 50.9 GPT-5 nano
- 43.6
Gemma 4 E2B
- 33.2
Gemma 4 31B IT
- 17.5
Gemma 4 12B
- 15.4
Gemma 3 27B
- 14.1 Ministral 3 8B
- 12.1 Claude Haiku 4.5
- 9.91 Ministral 3 3B
- 9.22
Qwen3-1.7B
- 9.22
Gemini 3.5 Flash-Lite
- 7.55 GPT-4.1 mini
- 7.33
Qwen3-4B
- 6.27 GPT-4.1 nano
- 5.89
Gemma 4 26B A4B
- 1.26
Qwen3-0.6B
- 1 GPT-5.5 95.9%
- 2 Claude Fable 5 95.9%
- 3
Gemini 3.6 Flash 95.7%
- 4 GPT-5.4 medium 95%
- 5
Gemini 3.5 Flash 94%
- 6 Claude Opus 5 92.7%
- 7 GPT-5.6 Sol 92.3%
- 8
Gemini 3 Flash 90.5%
- 9 GPT-5.6 Terra 89.8%
- 10 Grok 4.5 88.1%
- 11
Gemini 3.1 Pro 88%
- 12 GPT-5.6 Luna 84.1%
- 13 Claude Sonnet 5 78.3%
- 14 o3 66.2%
- 15
DeepSeek-V4-Pro 61.3%
- 16 gpt-oss-120b 55.8%
- 17 o4-mini 52.9%
- 18 GPT-5 nano medium 50.9%
- 19
Gemma 4 E2B 43.6%
- 20
Gemma 4 31B IT 33.2%
- 21
Gemma 4 12B 17.5%
- 22
Gemma 3 27B 15.4%
- 23 Ministral 3 8B 14.1%
- 24 Claude Haiku 4.5 12.1%
- 25 Ministral 3 3B 9.91%
- 26
Qwen3-1.7B 9.22%
- 27
Gemini 3.5 Flash-Lite 9.22%
- 28 GPT-4.1 mini 7.55%
- 29
Qwen3-4B 7.33%
- 30 GPT-4.1 nano 6.27%
- 31
Gemma 4 26B A4B 5.89%
- 32
Qwen3-0.6B 1.26%
Source: Official Decodability Assessment Benchmark leaderboard
- 95.9 GPT-5.5
- 95.9 Claude Fable 5
- 95.7
Gemini 3.6 Flash
- 95.0 GPT-5.4
- 94.0
Gemini 3.5 Flash
- 92.7 Claude Opus 5
- 92.3 GPT-5.6 Sol
- 90.5
Gemini 3 Flash
- 89.8 GPT-5.6 Terra
- 88.1 Grok 4.5
- 88.0
Gemini 3.1 Pro
- 84.1 GPT-5.6 Luna
- 78.3 Claude Sonnet 5
- 66.2 o3
- 61.3
DeepSeek-V4-Pro
- 55.8 gpt-oss-120b
- 52.9 o4-mini
- 50.9 GPT-5 nano
- 43.6
Gemma 4 E2B
- 33.2
Gemma 4 31B IT
- 17.5
Gemma 4 12B
- 15.4
Gemma 3 27B
- 12.1 Claude Haiku 4.5
- 9.22
Qwen3-1.7B
- 9.22
Gemini 3.5 Flash-Lite
- 7.55 GPT-4.1 mini
- 7.33
Qwen3-4B
- 6.27 GPT-4.1 nano
- 5.89
Gemma 4 26B A4B
- 1.26
Qwen3-0.6B
- 1 GPT-5.5 95.9%
- 2 Claude Fable 5 95.9%
- 3
Gemini 3.6 Flash 95.7%
- 4 GPT-5.4 medium 95%
- 5
Gemini 3.5 Flash 94%
- 6 Claude Opus 5 92.7%
- 7 GPT-5.6 Sol 92.3%
- 8
Gemini 3 Flash 90.5%
- 9 GPT-5.6 Terra 89.8%
- 10 Grok 4.5 88.1%
- 11
Gemini 3.1 Pro 88%
- 12 GPT-5.6 Luna 84.1%
- 13 Claude Sonnet 5 78.3%
- 14 o3 66.2%
- 15
DeepSeek-V4-Pro 61.3%
- 16 gpt-oss-120b 55.8%
- 17 o4-mini 52.9%
- 18 GPT-5 nano medium 50.9%
- 19
Gemma 4 E2B 43.6%
- 20
Gemma 4 31B IT 33.2%
- 21
Gemma 4 12B 17.5%
- 22
Gemma 3 27B 15.4%
- 23 Claude Haiku 4.5 12.1%
- 24
Qwen3-1.7B 9.22%
- 25
Gemini 3.5 Flash-Lite 9.22%
- 26 GPT-4.1 mini 7.55%
- 27
Qwen3-4B 7.33%
- 28 GPT-4.1 nano 6.27%
- 29
Gemma 4 26B A4B 5.89%
- 30
Qwen3-0.6B 1.26%
Source: Official Decodability Assessment Benchmark leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 95.9% | Apr 2026 | Official leaderboard | |
| 2 | Claude Fable 5 | 95.9% | Jun 2026 | Official leaderboard | |
| 3 | | 95.7% | Jul 2026 | Official leaderboard | |
| 4 | GPT-5.4 | 95% | medium | Mar 2026 | Official leaderboard |
| 5 | | 94% | May 2026 | Official leaderboard | |
| 6 | Claude Opus 5 | 92.7% | Jul 2026 | Official leaderboard | |
| 7 | GPT-5.6 Sol | 92.3% | Jul 2026 | Official leaderboard | |
| 8 | | 90.5% | Dec 2025 | Official leaderboard | |
| 9 | GPT-5.6 Terra | 89.8% | Jul 2026 | Official leaderboard | |
| 10 | Grok 4.5 | 88.1% | Jul 2026 | Official leaderboard | |
| 11 | | 88% | Feb 2026 | Official leaderboard | |
| 12 | GPT-5.6 Luna | 84.1% | Jul 2026 | Official leaderboard | |
| 13 | Claude Sonnet 5 | 78.3% | Jun 2026 | Official leaderboard | |
| 14 | o3 | 66.2% | Apr 2025 | Official leaderboard | |
| 15 | | 61.3% | Apr 2026 | Official leaderboard | |
| 16 | gpt-oss-120b | 55.8% | Aug 2025 | Official leaderboard | |
| 17 | o4-mini | 52.9% | Apr 2025 | Official leaderboard | |
| 18 | GPT-5 nano | 50.9% | medium | Aug 2025 | Official leaderboard |
| 19 | | 43.6% | Mar 2026 | Official leaderboard | |
| 20 | | 33.2% | Apr 2026 | Official leaderboard | |
| 21 | | 17.5% | Jun 2026 | Official leaderboard | |
| 22 | | 15.4% | Mar 2025 | Official leaderboard | |
| 23 | Ministral 3 8B | 14.1% | Official leaderboard | ||
| 24 | Claude Haiku 4.5 | 12.1% | Oct 2025 | Official leaderboard | |
| 25 | Ministral 3 3B | 9.91% | Official leaderboard | ||
| 26 | | 9.22% | Apr 2025 | Official leaderboard | |
| 27 | | 9.22% | Jul 2026 | Official leaderboard | |
| 28 | GPT-4.1 mini | 7.55% | Apr 2025 | Official leaderboard | |
| 29 | | 7.33% | Apr 2025 | Official leaderboard | |
| 30 | GPT-4.1 nano | 6.27% | Apr 2025 | Official leaderboard | |
| 31 | | 5.89% | Apr 2026 | Official leaderboard | |
| 32 | | 1.26% | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 95.9% | Apr 2026 | Official leaderboard | |
| 2 | Claude Fable 5 | 95.9% | Jun 2026 | Official leaderboard | |
| 3 | | 95.7% | Jul 2026 | Official leaderboard | |
| 4 | GPT-5.4 | 95% | medium | Mar 2026 | Official leaderboard |
| 5 | | 94% | May 2026 | Official leaderboard | |
| 6 | Claude Opus 5 | 92.7% | Jul 2026 | Official leaderboard | |
| 7 | GPT-5.6 Sol | 92.3% | Jul 2026 | Official leaderboard | |
| 8 | | 90.5% | Dec 2025 | Official leaderboard | |
| 9 | GPT-5.6 Terra | 89.8% | Jul 2026 | Official leaderboard | |
| 10 | Grok 4.5 | 88.1% | Jul 2026 | Official leaderboard | |
| 11 | | 88% | Feb 2026 | Official leaderboard | |
| 12 | GPT-5.6 Luna | 84.1% | Jul 2026 | Official leaderboard | |
| 13 | Claude Sonnet 5 | 78.3% | Jun 2026 | Official leaderboard | |
| 14 | o3 | 66.2% | Apr 2025 | Official leaderboard | |
| 15 | | 61.3% | Apr 2026 | Official leaderboard | |
| 16 | gpt-oss-120b | 55.8% | Aug 2025 | Official leaderboard | |
| 17 | o4-mini | 52.9% | Apr 2025 | Official leaderboard | |
| 18 | GPT-5 nano | 50.9% | medium | Aug 2025 | Official leaderboard |
| 19 | | 43.6% | Mar 2026 | Official leaderboard | |
| 20 | | 33.2% | Apr 2026 | Official leaderboard | |
| 21 | | 17.5% | Jun 2026 | Official leaderboard | |
| 22 | | 15.4% | Mar 2025 | Official leaderboard | |
| 23 | Claude Haiku 4.5 | 12.1% | Oct 2025 | Official leaderboard | |
| 24 | | 9.22% | Apr 2025 | Official leaderboard | |
| 25 | | 9.22% | Jul 2026 | Official leaderboard | |
| 26 | GPT-4.1 mini | 7.55% | Apr 2025 | Official leaderboard | |
| 27 | | 7.33% | Apr 2025 | Official leaderboard | |
| 28 | GPT-4.1 nano | 6.27% | Apr 2025 | Official leaderboard | |
| 29 | | 5.89% | Apr 2026 | Official leaderboard | |
| 30 | | 1.26% | Apr 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Decodability Assessment Benchmark leaderboard
Gemini 3 Flash on the official leaderboard passed 85% in December 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Decodability Assessment Benchmark 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 Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (32 entries).
- Pass Models scored 30 models we track, plus 2 other entries on its leaderboard.
- Pass Newest score The newest is from July 2026, for Claude Opus 5.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 5 (#11).
- Note Headroom Saturated. The best is 95.9%, past 85% since December 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on fab-ai.org: 30 rows for models we track and 2 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.