Benchmark Almanac

Base64Bench

Claude 3.7 Sonnet 75.9% leads since October 2025
Not in model cards

Models encode and decode base64 strings across different text and data formats. The evaluator measures exact matches and edit similarity.

In October 2025, Claude 3.7 Sonnet led perfect encoding and decoding at 75.9%. Claude Sonnet 4 scored 73.7%, followed by GPT-5 with minimal reasoning at 65.8%.

Released
October 2025
Kind
Following precise instructions
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5 #71 on the capability index
Last model added
August 2025
Scores refreshed
November 20th, 2026
3
Models scored in its paper

Claude 3.7 Sonnet leads with 75.9% among models released by August 2025

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in August 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude 3.7 Sonnet no reasoning or tools; perfect reconstruction 75.9%
  2. 2 Claude Sonnet 4 no reasoning or tools; perfect reconstruction 73.7%
  3. 3 GPT-5 minimal reasoning; perfect reconstruction 65.8%

Source: The Base64Bench paper

#ModelScoreSettingDateSource
1 Claude 3.7 Sonnet 75.9% no reasoning or tools; perfect reconstruction Feb 2025 Official leaderboard
2 Claude Sonnet 4 73.7% no reasoning or tools; perfect reconstruction May 2025 Official leaderboard
3 GPT-5 65.8% minimal reasoning; perfect reconstruction Aug 2025 Official leaderboard

Number one over time

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

Anthropic
Benchmark paper Not tested since Oct 2025

Source: The Base64Bench paper

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
In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Claude 3.7 Sonnet 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Claude 3.7 Sonnet

Source: Official Base64Bench 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 Instructions and chat

All 144 in Instructions and chat
  • IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy. Gemma 4 31B IT 98.9%
  • IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose). Flint 89.2%
  • MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
  • Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
  • AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics. MAI-Thinking-1 85%
  • MM-IFEval In use Multimodal models follow image-grounded instructions with exact output constraints. Checks mix rule-based verification and a judge model. GPT-4o 64.6%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 15 months ago, in August 2025, for GPT-5. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (3 entries).
  • Note Models scored Only 3 models we track.
  • Warning Newest score The newest came 15 months ago, in August 2025, for GPT-5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
  • Pass Headroom The best is 75.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on lesswrong.com: 3 rows for models we track 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