Benchmark Almanac

IOL-AI 2026

arvindcr4 19.8 tops its leaderboard
Not in model cards

Models infer linguistic rules from Olympiad problems and answer individual questions. The official competition combines exact match and character-level similarity.

Team arvindcr4 led the corrected July 2026 standings at 19.79 out of 100 using a four-bit Qwen2.5-14B-Instruct model.

Released
June 2026
Kind
Reasoning in many languages
Level
Competition
Scored
Checked automatically
Answers
Short answer
Tasks
Public, plus a private test set
Measures
Capability
Language
Many languages
In and out
Text → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
A host
In views
Many languages
48
Entries on its own leaderboard, 0 models we track

arvindcr4 tops the leaderboard with 19.8

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.

  1. 1 arvindcr4 19.8
  2. 2 BigRatz 18.9
  3. 3 hhhar 18.2
  4. 4 friedspaghetti 17.9
  5. 5 mastermind 16.7
  6. 6 Hul 16.7
  7. 7 jbuaba 16.5
  8. 8 attractordynamics 15.8
  9. 9 LOPE-NTU 15.1
  10. 10 srikarkashyap 14.7
  11. 11 cabanosss 14.6
  12. 12 randomizer 14.5
  13. 13 saital 14.5
  14. 14 Papajams 13.9
  15. 15 Agnivarcas 13.7
  16. 16 newendiesports 13.6
  17. 17 hotleafjuice 13.4
  18. 18 lim_sim 13.4
  19. 19 ahsanatiq98 13.3
  20. 20 ChrisR05 13.1
  21. 21 Curious 12.8
  22. 22 HamnaKaleem 12.2
  23. 23 KingpinFisk 12.0
  24. 24 SSOO 12.0
  25. 25 divagr1925 11.8
  26. 26 macbook 11.4
  27. 27 TJ 11.0
  28. 28 DanielTobi0 10.6
  29. 29 alyjimkh 10.1
  30. 30 raf 9.63
  31. 31 Baseline-Qwen2.5-14B-AWQ 9.40
  32. 32 lindaz 9.40
  33. 33 rpant 8.43
  34. 34 Tiny-Aya-R1 8.24
  35. 35 BaselinesTinyAya 8.12
  36. 36 jithinjames 7.69
  37. 37 MikCil 7.53
  38. 38 Baseline-Qwen2.5-7B-Instruct 7.10
  39. 39 workerplacemint 6.57
  40. 40 Pika 5.56
  41. 41 Baseline-Qwen2.5-1.5B-Instruct 4.00
  42. 42 pytransformer1 2.45
  43. 43 parinzee 1.87
  44. 44 iolai-test 1.78
  45. 45 ShayanShamsi 0.00
  46. 46 atanb27 0.00
  47. 47 emharsha1812 0.00
  48. 48 abhiandprusehf 0.00

Source: Official IOL-AI 2026 leaderboard

#EntryScoreSettingSubmitted byDateSource
1 arvindcr4 19.8 arvindcr4 arvindcr4 Jul 2026 Official leaderboard
2 BigRatz 18.9 BigRatz BigRatz Jul 2026 Official leaderboard
3 hhhar 18.2 hhhar hhhar Jul 2026 Official leaderboard
4 friedspaghetti 17.9 friedspaghetti friedspaghetti Jul 2026 Official leaderboard
5 mastermind 16.7 mastermind mastermind Jul 2026 Official leaderboard
6 Hul 16.7 Hul Hul Jul 2026 Official leaderboard
7 jbuaba 16.5 jbuaba jbuaba Jul 2026 Official leaderboard
8 attractordynamics 15.8 attractordynamics attractordynamics Jul 2026 Official leaderboard
9 LOPE-NTU 15.1 LOPE-NTU LOPE-NTU Jul 2026 Official leaderboard
10 srikarkashyap 14.7 srikarkashyap srikarkashyap Jul 2026 Official leaderboard
11 cabanosss 14.6 cabanosss cabanosss Jul 2026 Official leaderboard
12 randomizer 14.5 randomizer randomizer Jul 2026 Official leaderboard
13 saital 14.5 saital saital Jul 2026 Official leaderboard
14 Papajams 13.9 Papajams Papajams Jul 2026 Official leaderboard
15 Agnivarcas 13.7 Agnivarcas Agnivarcas Jul 2026 Official leaderboard
16 newendiesports 13.6 newendiesports newendiesports Jul 2026 Official leaderboard
17 hotleafjuice 13.4 hotleafjuice hotleafjuice Jul 2026 Official leaderboard
18 lim_sim 13.4 lim_sim lim_sim Jul 2026 Official leaderboard
19 ahsanatiq98 13.3 ahsanatiq98 ahsanatiq98 Jul 2026 Official leaderboard
20 ChrisR05 13.1 ChrisR05 ChrisR05 Jul 2026 Official leaderboard
21 Curious 12.8 Curious Curious Jul 2026 Official leaderboard
22 HamnaKaleem 12.2 HamnaKaleem HamnaKaleem Jul 2026 Official leaderboard
23 KingpinFisk 12.0 KingpinFisk KingpinFisk Jul 2026 Official leaderboard
24 SSOO 12.0 SSOO SSOO Jul 2026 Official leaderboard
25 divagr1925 11.8 divagr1925 divagr1925 Jul 2026 Official leaderboard
26 macbook 11.4 macbook macbook Jul 2026 Official leaderboard
27 TJ 11.0 TJ TJ Jul 2026 Official leaderboard
28 DanielTobi0 10.6 DanielTobi0 DanielTobi0 Jul 2026 Official leaderboard
29 alyjimkh 10.1 alyjimkh alyjimkh Jul 2026 Official leaderboard
30 raf 9.63 raf raf Jul 2026 Official leaderboard
31 Baseline-Qwen2.5-14B-AWQ 9.40 Baseline-Qwen2.5-14B-AWQ Baseline-Qwen2.5-14B-AWQ Jul 2026 Official leaderboard
32 lindaz 9.40 lindaz lindaz Jul 2026 Official leaderboard
33 rpant 8.43 rpant rpant Jul 2026 Official leaderboard
34 Tiny-Aya-R1 8.24 Tiny-Aya-R1 Tiny-Aya-R1 Jul 2026 Official leaderboard
35 BaselinesTinyAya 8.12 BaselinesTinyAya BaselinesTinyAya Jul 2026 Official leaderboard
36 jithinjames 7.69 jithinjames jithinjames Jul 2026 Official leaderboard
37 MikCil 7.53 MikCil MikCil Jul 2026 Official leaderboard
38 Baseline-Qwen2.5-7B-Instruct 7.10 Baseline-Qwen2.5-7B-Instruct Baseline-Qwen2.5-7B-Instruct Jul 2026 Official leaderboard
39 workerplacemint 6.57 workerplacemint workerplacemint Jul 2026 Official leaderboard
40 Pika 5.56 Pika Pika Jul 2026 Official leaderboard
41 Baseline-Qwen2.5-1.5B-Instruct 4.00 Baseline-Qwen2.5-1.5B-Instruct Baseline-Qwen2.5-1.5B-Instruct Jul 2026 Official leaderboard
42 pytransformer1 2.45 pytransformer1 pytransformer1 Jul 2026 Official leaderboard
43 parinzee 1.87 parinzee parinzee Jul 2026 Official leaderboard
44 iolai-test 1.78 iolai-test iolai-test Jul 2026 Official leaderboard
45 ShayanShamsi 0.00 ShayanShamsi ShayanShamsi Jul 2026 Official leaderboard
46 atanb27 0.00 atanb27 atanb27 Jul 2026 Official leaderboard
47 emharsha1812 0.00 emharsha1812 emharsha1812 Jul 2026 Official leaderboard
48 abhiandprusehf 0.00 abhiandprusehf abhiandprusehf Jul 2026 Official 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 Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

Data audit

All 8 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 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (48 entries).
  • Pass Models scored 48 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on iolai.org: 48 entries at the last read, none a model we track.
  • 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