Benchmark Almanac

ELI5 Arena

Gemini 4 Argon 1,691 leads since September 2026
Not in model cards

Models explain concepts in simple language. Pairwise votes determine the published Arena rating.

The official API publishes an Arena rating, confidence interval and vote count. Voter identity requires confirmation from the board description.

Made by
Kaggle
Kind
Overall chat quality
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
September 2026
Scores refreshed
November 12th, 2026
18
Models scored on its own leaderboard

Gemini 4 Argon leads with 1,691

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

18 models. Scroll sideways for the rest. Bars start at 1,300.

  1. 1,691 Gemini 4 Argon
  2. 1,689 GPT-5.6 Sol
  3. 1,656 Qwen 3.8 Max
  4. 1,596 GLM-5.3
  5. 1,591 GPT-5.6 Terra
  6. 1,583 Gemini 3.8 Flash
  7. 1,567 Claude Fable 5.1
  8. 1,468 Gemini 3.1 Pro
  9. 1,463 GPT-6 Astra
  10. 1,463 GPT-5 Pro
  11. 1,450 GPT-5.5
  12. 1,444 Claude Opus 5.5
  13. 1,436 Claude Opus 5
  14. 1,422 GPT-6 Luna
  15. 1,416 Claude Sonnet 5
  16. 1,407 Claude Sonnet 5.5
  17. 1,371 Grok 4.7
  18. 1,344 GPT-6.1 Sol

Bars start at 1,300.

  1. 1 Gemini 4 Argon Gemini 4 Argon High Reasoning 1,691
  2. 2 GPT-5.6 Sol GPT-5.6 Sol Max Reasoning 1,689
  3. 3 Qwen 3.8 Max Qwen 3.8 Max Xhigh Reasoning 1,656
  4. 4 GLM-5.3 GLM-5.3 Max Reasoning 1,596
  5. 5 GPT-5.6 Terra GPT-5.6 Terra High Reasoning 1,591
  6. 6 Gemini 3.8 Flash Gemini 3.8 Flash High Reasoning 1,583
  7. 7 Claude Fable 5.1 Claude Fable 5.1 Max Reasoning 1,567
  8. 8 Gemini 3.1 Pro Gemini 3.1 Pro Preview High Reasoning 1,468
  9. 9 GPT-6 Astra GPT-6 Astra Max Reasoning 1,463
  10. 10 GPT-5 Pro GPT-5 Pro High Reasoning 1,463
  11. 11 GPT-5.5 GPT-5.5 High Reasoning 1,450
  12. 12 Claude Opus 5.5 Claude Opus 5.5 Max Reasoning 1,444
  13. 13 Claude Opus 5 Claude Opus 5 Max Reasoning 1,436
  14. 14 GPT-6 Luna GPT-6 Luna Max Reasoning 1,422
  15. 15 Claude Sonnet 5 Claude Sonnet 5 High Reasoning 1,416
  16. 16 Claude Sonnet 5.5 Claude Sonnet 5.5 Max Reasoning 1,407
  17. 17 Grok 4.7 Grok 4.7 Xhigh Reasoning 1,371
  18. 18 GPT-6.1 Sol GPT-6.1 Sol Max Reasoning 1,344

Source: Official ELI5 Arena leaderboard

#ModelScoreSettingDateSource
1 Gemini 4 Argon 1,691 Gemini 4 Argon High Reasoning Sep 2026 Official leaderboard
2 GPT-5.6 Sol 1,689 GPT-5.6 Sol Max Reasoning Jul 2026 Official leaderboard
3 Qwen 3.8 Max 1,656 Qwen 3.8 Max Xhigh Reasoning Aug 2026 Official leaderboard
4 GLM-5.3 1,596 GLM-5.3 Max Reasoning Aug 2026 Official leaderboard
5 GPT-5.6 Terra 1,591 GPT-5.6 Terra High Reasoning Jul 2026 Official leaderboard
6 Gemini 3.8 Flash 1,583 Gemini 3.8 Flash High Reasoning Sep 2026 Official leaderboard
7 Claude Fable 5.1 1,567 Claude Fable 5.1 Max Reasoning Sep 2026 Official leaderboard
8 Gemini 3.1 Pro 1,468 Gemini 3.1 Pro Preview High Reasoning Feb 2026 Official leaderboard
9 GPT-6 Astra 1,463 GPT-6 Astra Max Reasoning Sep 2026 Official leaderboard
10 GPT-5 Pro 1,463 GPT-5 Pro High Reasoning Oct 2025 Official leaderboard
11 GPT-5.5 1,450 GPT-5.5 High Reasoning Apr 2026 Official leaderboard
12 Claude Opus 5.5 1,444 Claude Opus 5.5 Max Reasoning Sep 2026 Official leaderboard
13 Claude Opus 5 1,436 Claude Opus 5 Max Reasoning Jul 2026 Official leaderboard
14 GPT-6 Luna 1,422 GPT-6 Luna Max Reasoning Sep 2026 Official leaderboard
15 Claude Sonnet 5 1,416 Claude Sonnet 5 High Reasoning Jun 2026 Official leaderboard
16 Claude Sonnet 5.5 1,407 Claude Sonnet 5.5 Max Reasoning Sep 2026 Official leaderboard
17 Grok 4.7 1,371 Grok 4.7 Xhigh Reasoning Sep 2026 Official leaderboard
18 GPT-6.1 Sol 1,344 GPT-6.1 Sol Max Reasoning Sep 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.

OpenAI Google DeepMind
Own leaderboard 4 leaders
Gemini 4 Argon 1,691

Source: Official ELI5 Arena 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
1,300 1,400 1,500 1,600 1,700 2026 1,300 1,400 1,500 1,600 1,700 2026

Source: Official ELI5 Arena 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 Instructions and chat

All 81 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). Nemotron-Cascade 2 30B-A3B 82.9%
  • 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%
  • IFStruct In use Models generate JSON or YAML that must follow a requested schema and phrasing constraints, without constrained decoding. A response passes only if every structural constraint holds. Gemma 4 31B IT 95.9%