Benchmark Almanac

IOI v2 (Vals)

GPT-6 Astra 100% leads since October 2026
Not in model cards

Agents solve 18 International Olympiad in Informatics problems from 2024, 2025 and 2026 in C++ inside OpenCode. Official tests and graders score the final solution by subtask after the run.

Unlike v1 there is no interactive grading tool, and Vals says the two harnesses are not comparable. Score is the mean of three yearly scores. Released between August 9th, 2026 and October 29th, 2026.

Made by
Vals AI
Released
October 2026
Kind
Competitive programming
Level
Competition
Scored
Checked automatically
Answers
Code
Tasks
All public
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
October 2026
Scores refreshed
November 12th, 2026
45
Models scored on its own leaderboard

2 models share the top score of 100%

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. Every run is in the next chart.

45 models. Scroll sideways for the rest.

  1. 100.0 GPT-6 Astra
  2. 100.0 Gemini 4 Argon
  3. 96.9 GPT-6.1 Sol
  4. 95.1 Claude Opus 5.5
  5. 91.2 GPT-5.6 Sol
  6. 90.8 Claude Fable 5.1
  7. 87.6 GPT-5.6 Terra
  8. 84.3 Claude Opus 5
  9. 83.1 Claude Sonnet 5.5
  10. 82.6 GPT-6 Sol
  11. 81.9 Kimi K3.1 Pro
  12. 79.8 Muse Wonder Full
  13. 68.9 Qwen 3.8 Max
  14. 68.4 GLM-5.3
  15. 67.8 Gemini 3.7 Flash
  16. 66.9 Muse Wonder
  17. 61.8 GPT-5.6 Luna
  18. 59.3 Tencent Hy4 preview
  19. 57.7 Grok 4.7
  20. 56.9 Gemini 3.8 Flash
  21. 56.6 Muse Spark 1.3
  22. 55.6 GPT-6 Luna
  23. 53.8 GPT-5.3 Codex
  24. 52.5 GLM-5.3-Flash
  25. 51.8 Gemini 3.1 Pro
  26. 51.6 DeepSeek V4 Pro 0813
  27. 48.9 Kimi K3
  28. 47.7 MiMo-V2.6 Flash
  29. 47.6 Grok 4.6
  30. 47.3 Claude Haiku 5.5
  31. 46.3 Ember-1
  32. 45.3 Mistral Large 4 Preview
  33. 45.0 Claude Sonnet 5
  34. 40.6 Grok 4.5
  35. 40.3 DeepSeek V4.1 Flash
  36. 39.3 MiMo-V2.6 Pro
  37. 39.1 Qwen 3.8 27B
  38. 38.1 Step 5 Preview
  39. 35.1 Gemini 3.6 Flash
  40. 32.7 DeepSeek V4 Flash 0731
  41. 22.8 Beam 1.0
  42. 21.8 Muse Spark 1.2
  43. 14.9 Inkling
  44. 9.33 Inkling-Small
  45. 2.44 Mercury 2.5
  1. 1 GPT-6 Astra 100%
  2. 2 Gemini 4 Argon 100%
  3. 3 GPT-6.1 Sol 96.9%
  4. 4 Claude Opus 5.5 95.1%
  5. 5 GPT-5.6 Sol 91.2%
  6. 6 Claude Fable 5.1 90.8%
  7. 7 GPT-5.6 Terra 87.6%
  8. 8 Claude Opus 5 84.3%
  9. 9 Claude Sonnet 5.5 83.1%
  10. 10 GPT-6 Sol 82.6%
  11. 11 Kimi K3.1 Pro 81.9%
  12. 12 Muse Wonder Full 79.8%
  13. 13 Qwen 3.8 Max 68.9%
  14. 14 GLM-5.3 68.4%
  15. 15 Gemini 3.7 Flash 67.8%
  16. 16 Muse Wonder 66.9%
  17. 17 GPT-5.6 Luna 61.8%
  18. 18 Tencent Hy4 preview 59.3%
  19. 19 Grok 4.7 57.7%
  20. 20 Gemini 3.8 Flash 56.9%
  21. 21 Muse Spark 1.3 max 56.6%
  22. 22 GPT-6 Luna 55.6%
  23. 23 GPT-5.3 Codex 53.8%
  24. 24 GLM-5.3-Flash 52.5%
  25. 25 Gemini 3.1 Pro 51.8%
  26. 26 DeepSeek V4 Pro 0813 51.6%
  27. 27 Kimi K3 48.9%
  28. 28 MiMo-V2.6 Flash 47.7%
  29. 29 Grok 4.6 47.6%
  30. 30 Claude Haiku 5.5 47.3%
  31. 31 Ember-1 46.3%
  32. 32 Mistral Large 4 Preview 45.3%
  33. 33 Claude Sonnet 5 45%
  34. 34 Grok 4.5 40.6%
  35. 35 DeepSeek V4.1 Flash 40.3%
  36. 36 MiMo-V2.6 Pro 39.3%
  37. 37 Qwen 3.8 27B 39.1%
  38. 38 Step 5 Preview 38.1%
  39. 39 Gemini 3.6 Flash 35.1%
  40. 40 DeepSeek V4 Flash 0731 32.7%
  41. 41 Beam 1.0 22.8%
  42. 42 Muse Spark 1.2 21.8%
  43. 43 Inkling 14.9%
  44. 44 Inkling-Small 9.33%
  45. 45 Mercury 2.5 2.44%

Source: Official IOI v2 (Vals) leaderboard

#ModelScoreSettingDateSource
1 GPT-6 Astra 100% Sep 2026 Official leaderboard
2 Gemini 4 Argon 100% Sep 2026 Official leaderboard
3 GPT-6.1 Sol 96.9% Sep 2026 Official leaderboard
4 Claude Opus 5.5 95.1% Sep 2026 Official leaderboard
5 GPT-5.6 Sol 91.2% Jul 2026 Official leaderboard
6 Claude Fable 5.1 90.8% Sep 2026 Official leaderboard
7 GPT-5.6 Terra 87.6% Jul 2026 Official leaderboard
8 Claude Opus 5 84.3% Jul 2026 Official leaderboard
9 Claude Sonnet 5.5 83.1% Sep 2026 Official leaderboard
10 GPT-6 Sol 82.6% Sep 2026 Official leaderboard
11 Kimi K3.1 Pro 81.9% Oct 2026 Official leaderboard
12 Muse Wonder Full 79.8% Oct 2026 Official leaderboard
13 Qwen 3.8 Max 68.9% Aug 2026 Official leaderboard
14 GLM-5.3 68.4% Aug 2026 Official leaderboard
15 Gemini 3.7 Flash 67.8% Aug 2026 Official leaderboard
16 Muse Wonder 66.9% Oct 2026 Official leaderboard
17 GPT-5.6 Luna 61.8% Jul 2026 Official leaderboard
18 Tencent Hy4 preview 59.3% Aug 2026 Official leaderboard
19 Grok 4.7 57.7% Sep 2026 Official leaderboard
20 Gemini 3.8 Flash 56.9% Sep 2026 Official leaderboard
21 Muse Spark 1.3 56.6% max Sep 2026 Official leaderboard
22 GPT-6 Luna 55.6% Sep 2026 Official leaderboard
23 GPT-5.3 Codex 53.8% Feb 2026 Official leaderboard
24 GLM-5.3-Flash 52.5% Aug 2026 Official leaderboard
25 Gemini 3.1 Pro 51.8% Feb 2026 Official leaderboard
26 DeepSeek V4 Pro 0813 51.6% Aug 2026 Official leaderboard
27 Kimi K3 48.9% Jul 2026 Official leaderboard
28 MiMo-V2.6 Flash 47.7% Sep 2026 Official leaderboard
29 Grok 4.6 47.6% Aug 2026 Official leaderboard
30 Claude Haiku 5.5 47.3% Oct 2026 Official leaderboard
31 Ember-1 46.3% Sep 2026 Official leaderboard
32 Mistral Large 4 Preview 45.3% Oct 2026 Official leaderboard
33 Claude Sonnet 5 45% Jun 2026 Official leaderboard
34 Grok 4.5 40.6% Jul 2026 Official leaderboard
35 DeepSeek V4.1 Flash 40.3% Sep 2026 Official leaderboard
36 MiMo-V2.6 Pro 39.3% Sep 2026 Official leaderboard
37 Qwen 3.8 27B 39.1% Aug 2026 Official leaderboard
38 Step 5 Preview 38.1% Sep 2026 Official leaderboard
39 Gemini 3.6 Flash 35.1% Jul 2026 Official leaderboard
40 DeepSeek V4 Flash 0731 32.7% Jul 2026 Official leaderboard
41 Beam 1.0 22.8% Oct 2026 Official leaderboard
42 Muse Spark 1.2 21.8% Aug 2026 Official leaderboard
43 Inkling 14.9% Jul 2026 Official leaderboard
44 Inkling-Small 9.33% Jul 2026 Official leaderboard
45 Mercury 2.5 2.44% Sep 2026 Official leaderboard

Accuracy against latency

The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.

0% 20% 40% 60% 80% 100% 1001,00010K100K Latency (mean per test) (s), log scale, lower is better Accuracy GPT-5.3 Codex: Accuracy 53.8%, latency (mean per test) 1,792 s Claude Sonnet 5: Accuracy 45%, latency (mean per test) 3,584 s Grok 4.5: Accuracy 40.6%, latency (mean per test) 5,195 s GPT-5.6 Luna: Accuracy 61.8%, latency (mean per test) 4,175 s GPT-5.6 Sol: Accuracy 91.2%, latency (mean per test) 3,712 s GPT-5.6 Terra: Accuracy 87.6%, latency (mean per test) 4,993 s Inkling: Accuracy 14.9%, latency (mean per test) 1,812 s Inkling-Small: Accuracy 9.33%, latency (mean per test) 678 s Kimi K3: Accuracy 48.9%, latency (mean per test) 16K s Gemini 3.6 Flash: Accuracy 35.1%, latency (mean per test) 2,903 s Claude Opus 5: Accuracy 84.3%, latency (mean per test) 3,402 s DeepSeek V4 Flash 0731: Accuracy 32.7%, latency (mean per test) 1,663 s Qwen 3.8 Max: Accuracy 68.9%, latency (mean per test) 6,398 s Muse Spark 1.2: Accuracy 21.8%, latency (mean per test) 1,535 s Grok 4.6: Accuracy 47.6%, latency (mean per test) 14K s DeepSeek V4 Pro 0813: Accuracy 51.6%, latency (mean per test) 4,046 s Gemini 3.7 Flash: Accuracy 67.8%, latency (mean per test) 1,269 s GLM-5.3: Accuracy 68.4%, latency (mean per test) 6,375 s Qwen 3.8 27B: Accuracy 39.1%, latency (mean per test) 5,925 s GLM-5.3-Flash: Accuracy 52.5%, latency (mean per test) 5,549 s Tencent Hy4 preview: Accuracy 59.3%, latency (mean per test) 3,633 s Claude Fable 5.1: Accuracy 90.8%, latency (mean per test) 1,806 s Muse Spark 1.3 (max): Accuracy 56.6%, latency (mean per test) 1,738 s Muse Spark 1.3: Accuracy 43.9%, latency (mean per test) 1,791 s GPT-6 Astra: Accuracy 100%, latency (mean per test) 1,900 s DeepSeek V4.1 Flash: Accuracy 40.3%, latency (mean per test) 1,110 s Step 5 Preview: Accuracy 38.1%, latency (mean per test) 4,821 s Grok 4.7: Accuracy 57.7%, latency (mean per test) 2,809 s MiMo-V2.6 Flash: Accuracy 47.7%, latency (mean per test) 6,522 s MiMo-V2.6 Pro: Accuracy 39.3%, latency (mean per test) 8,783 s GPT-6 Luna: Accuracy 55.6%, latency (mean per test) 2,147 s GPT-6 Sol: Accuracy 82.6%, latency (mean per test) 1,838 s Ember-1: Accuracy 46.3%, latency (mean per test) 6,401 s Claude Sonnet 5.5: Accuracy 83.1%, latency (mean per test) 2,751 s GPT-6.1 Sol: Accuracy 96.9%, latency (mean per test) 1,891 s Mistral Large 4 Preview: Accuracy 45.3%, latency (mean per test) 5,024 s Claude Haiku 5.5: Accuracy 47.3%, latency (mean per test) 754 s Muse Wonder: Accuracy 66.9%, latency (mean per test) 1,502 s Muse Wonder Full: Accuracy 79.8%, latency (mean per test) 5,446 s Kimi K3.1 Pro: Accuracy 81.9%, latency (mean per test) 2,965 s Gemini 3.1 Pro: Accuracy 51.8%, latency (mean per test) 723 s Gemini 3.8 Flash: Accuracy 56.9%, latency (mean per test) 860 s Mercury 2.5: Accuracy 2.44%, latency (mean per test) 243 s Claude Opus 5.5: Accuracy 95.1%, latency (mean per test) 1,035 s Gemini 4 Argon: Accuracy 100%, latency (mean per test) 1,459 s Beam 1.0: Accuracy 22.8%, latency (mean per test) 433 s Gemini 4 ArgonClaude Opus 5.5Gemini 3.8 FlashGemini 3.1 ProBeam 1.0Mercury 2.5 0% 20% 40% 60% 80% 100% 1001,00010K100K Latency (mean per test) (s), log scale, lower is better Accuracy GPT-5.3 Codex: Accuracy 53.8%, latency (mean per test) 1,792 s Claude Sonnet 5: Accuracy 45%, latency (mean per test) 3,584 s Grok 4.5: Accuracy 40.6%, latency (mean per test) 5,195 s GPT-5.6 Luna: Accuracy 61.8%, latency (mean per test) 4,175 s GPT-5.6 Sol: Accuracy 91.2%, latency (mean per test) 3,712 s GPT-5.6 Terra: Accuracy 87.6%, latency (mean per test) 4,993 s Inkling: Accuracy 14.9%, latency (mean per test) 1,812 s Inkling-Small: Accuracy 9.33%, latency (mean per test) 678 s Kimi K3: Accuracy 48.9%, latency (mean per test) 16K s Gemini 3.6 Flash: Accuracy 35.1%, latency (mean per test) 2,903 s Claude Opus 5: Accuracy 84.3%, latency (mean per test) 3,402 s DeepSeek V4 Flash 0731: Accuracy 32.7%, latency (mean per test) 1,663 s Qwen 3.8 Max: Accuracy 68.9%, latency (mean per test) 6,398 s Muse Spark 1.2: Accuracy 21.8%, latency (mean per test) 1,535 s Grok 4.6: Accuracy 47.6%, latency (mean per test) 14K s DeepSeek V4 Pro 0813: Accuracy 51.6%, latency (mean per test) 4,046 s Gemini 3.7 Flash: Accuracy 67.8%, latency (mean per test) 1,269 s GLM-5.3: Accuracy 68.4%, latency (mean per test) 6,375 s Qwen 3.8 27B: Accuracy 39.1%, latency (mean per test) 5,925 s GLM-5.3-Flash: Accuracy 52.5%, latency (mean per test) 5,549 s Tencent Hy4 preview: Accuracy 59.3%, latency (mean per test) 3,633 s Claude Fable 5.1: Accuracy 90.8%, latency (mean per test) 1,806 s Muse Spark 1.3 (max): Accuracy 56.6%, latency (mean per test) 1,738 s Muse Spark 1.3: Accuracy 43.9%, latency (mean per test) 1,791 s GPT-6 Astra: Accuracy 100%, latency (mean per test) 1,900 s DeepSeek V4.1 Flash: Accuracy 40.3%, latency (mean per test) 1,110 s Step 5 Preview: Accuracy 38.1%, latency (mean per test) 4,821 s Grok 4.7: Accuracy 57.7%, latency (mean per test) 2,809 s MiMo-V2.6 Flash: Accuracy 47.7%, latency (mean per test) 6,522 s MiMo-V2.6 Pro: Accuracy 39.3%, latency (mean per test) 8,783 s GPT-6 Luna: Accuracy 55.6%, latency (mean per test) 2,147 s GPT-6 Sol: Accuracy 82.6%, latency (mean per test) 1,838 s Ember-1: Accuracy 46.3%, latency (mean per test) 6,401 s Claude Sonnet 5.5: Accuracy 83.1%, latency (mean per test) 2,751 s GPT-6.1 Sol: Accuracy 96.9%, latency (mean per test) 1,891 s Mistral Large 4 Preview: Accuracy 45.3%, latency (mean per test) 5,024 s Claude Haiku 5.5: Accuracy 47.3%, latency (mean per test) 754 s Muse Wonder: Accuracy 66.9%, latency (mean per test) 1,502 s Muse Wonder Full: Accuracy 79.8%, latency (mean per test) 5,446 s Kimi K3.1 Pro: Accuracy 81.9%, latency (mean per test) 2,965 s Gemini 3.1 Pro: Accuracy 51.8%, latency (mean per test) 723 s Gemini 3.8 Flash: Accuracy 56.9%, latency (mean per test) 860 s Mercury 2.5: Accuracy 2.44%, latency (mean per test) 243 s Claude Opus 5.5: Accuracy 95.1%, latency (mean per test) 1,035 s Gemini 4 Argon: Accuracy 100%, latency (mean per test) 1,459 s Beam 1.0: Accuracy 22.8%, latency (mean per test) 433 s Gemini 4 ArgonClaude Opus 5.5Gemini 3.8 FlashGemini 3.1 ProBeam 1.0Mercury 2.5
ModelSettingAccuracyLatency (mean per test)
Gemini 4 Argon 100% 1,459 s
GPT-6 Astra 100% 1,900 s
GPT-6.1 Sol 96.9% 1,891 s
Claude Opus 5.5 95.1% 1,035 s
GPT-5.6 Sol 91.2% 3,712 s
Claude Fable 5.1 90.8% 1,806 s
GPT-5.6 Terra 87.6% 4,993 s
Claude Opus 5 84.3% 3,402 s
Claude Sonnet 5.5 83.1% 2,751 s
GPT-6 Sol 82.6% 1,838 s
Kimi K3.1 Pro 81.9% 2,965 s
Muse Wonder Full 79.8% 5,446 s
Qwen 3.8 Max 68.9% 6,398 s
GLM-5.3 68.4% 6,375 s
Gemini 3.7 Flash 67.8% 1,269 s
Muse Wonder 66.9% 1,502 s
GPT-5.6 Luna 61.8% 4,175 s
Tencent Hy4 preview 59.3% 3,633 s
Grok 4.7 57.7% 2,809 s
Gemini 3.8 Flash 56.9% 860.47 s
Muse Spark 1.3 max 56.6% 1,738 s
GPT-6 Luna 55.6% 2,147 s
GPT-5.3 Codex 53.8% 1,792 s
GLM-5.3-Flash 52.5% 5,549 s
Gemini 3.1 Pro 51.8% 722.64 s
DeepSeek V4 Pro 0813 51.6% 4,046 s
Kimi K3 48.9% 15,509 s
MiMo-V2.6 Flash 47.7% 6,522 s
Grok 4.6 47.6% 14,234 s
Claude Haiku 5.5 47.3% 753.82 s
Ember-1 46.3% 6,401 s
Mistral Large 4 Preview 45.3% 5,024 s
Claude Sonnet 5 45% 3,584 s
Muse Spark 1.3 43.9% 1,791 s
Grok 4.5 40.6% 5,195 s
DeepSeek V4.1 Flash 40.3% 1,110 s
MiMo-V2.6 Pro 39.3% 8,783 s
Qwen 3.8 27B 39.1% 5,925 s
Step 5 Preview 38.1% 4,821 s
Gemini 3.6 Flash 35.1% 2,903 s
DeepSeek V4 Flash 0731 32.7% 1,663 s
Beam 1.0 22.8% 432.59 s
Muse Spark 1.2 21.8% 1,535 s
Inkling 14.9% 1,812 s
Inkling-Small 9.3% 678.06 s
Mercury 2.5 2.4% 242.94 s

The best score, 100%, costs $5.31 a task

Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol comes within 3.1 points of the best for $1.26 a task, 4 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI Inception Labs Google DeepMind Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Gemini 4 Argon GPT-6.1 Sol GPT-5.6 Luna GPT-6 Luna Mercury 2.5 0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Gemini 4 Argon GPT-5.6 Luna

Source: Official IOI v2 (Vals) leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6 Astra 100% $6.50 90,362
Gemini 4 Argon 100% $5.31 103,339
GPT-6.1 Sol 96.9% $1.26 87,651
Claude Opus 5.5 95.1% $4.35 124,041
GPT-5.6 Sol 91.2% $7.98 250,540
Claude Fable 5.1 90.8% $11 163,700
GPT-5.6 Terra 87.6% $8.66 380,971
Claude Opus 5 84.3% $16 231,030
Claude Sonnet 5.5 83.1% $5.81 252,017
GPT-6 Sol 82.6% $2.70 169,175
Kimi K3.1 Pro 81.9% $5.02 266,427
Muse Wonder Full 79.8% $7.08 108,796
Qwen 3.8 Max 68.9% $9.47 257,432
GLM-5.3 68.4% $7.67 326,373
Gemini 3.7 Flash 67.8% $3.40 120,010
Muse Wonder 66.9% $4.54 120,835
GPT-5.6 Luna 61.8% $0.58 226,578
Tencent Hy4 preview 59.3% $1.35 202,586
Grok 4.7 57.7% $13 195,973
Gemini 3.8 Flash 56.9% $3.98 150,773
Muse Spark 1.3 max 56.6% $1.73 201,652
GPT-6 Luna 55.6% $0.20 237,839
GPT-5.3 Codex 53.8% $2.68 115,743
GLM-5.3-Flash 52.5% $0.43 369,012
Gemini 3.1 Pro 51.8% $1.25 53,550
DeepSeek V4 Pro 0813 51.6% $2.15 289,819
Kimi K3 48.9% $14 355,820
MiMo-V2.6 Flash 47.7% $0.22 237,014
Grok 4.6 47.6% $8.18 833,582
Claude Haiku 5.5 47.3% $0.83 248,421
Ember-1 46.3% $24 304,986
Mistral Large 4 Preview 45.3% $2.73 481,324
Claude Sonnet 5 45% $13 347,431
Muse Spark 1.3 43.9% $2.36 332,486
Grok 4.5 40.6% $5.64 253,212
DeepSeek V4.1 Flash 40.3% $0.24 161,933
MiMo-V2.6 Pro 39.3% $0.84 480,854
Qwen 3.8 27B 39.1% $3.55 621,908
Step 5 Preview 38.1% $2.03 325,917
Gemini 3.6 Flash 35.1% $8.67 169,385
DeepSeek V4 Flash 0731 32.7% $0.37 172,784
Beam 1.0 22.8% 71,964
Muse Spark 1.2 21.8% $2.64 177,630
Inkling 14.9% $1.71 109,539
Inkling-Small 9.33% $0.34 86,571
Mercury 2.5 2.44% $0.16 34,832

Number one over time

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

OpenAI
Own leaderboard Passed 85% in Oct 2026, by GPT-6 Astra
GPT-6 Astra 100%

Source: Official IOI v2 (Vals) leaderboard

GPT-5.6 Sol on the official leaderboard passed 85% in July 2026

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 2027 Near the ceiling (85%) GPT-6 Astra GPT-5.6 Sol GPT-5.3 Codex 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-6 Astra GPT-5.6 Sol

Source: Official IOI v2 (Vals) 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.

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

xAI Google DeepMind OpenAI Anthropic
IOI v2 (Vals) Passed 85% in Oct 2026, by GPT-6 Astra
GPT-6 Astra 100%
IOI (Vals) Passed 85% in Jul 2026, by GPT-5.6 Sol
Claude Opus 5 91.7%
IOI v2 (Vals) Passed 85% in Oct 2026, by GPT-6 Astra
GPT-6 Astra 100%

Source: Official leaderboards

Replaces IOI (Vals)

More in Coding

All 282 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471