Skip to main content
benchlm.ai

Vals IOI (IOI)

Based on the International Olympiad in Informatics

Data verified

How BenchLM shows IOI

BenchLM mirrors the public Vals AI IOI leaderboard captured from https://www.vals.ai/benchmarks/ioi and updated by Vals on July 9, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

IOI is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

58 Vals rows3 task viewspublic datasetTasks: Overall, IOI 2024, IOI 2025Display only
IOI on Vals AIVals methodologyVals home

IOI score on IOI — July 9, 2026

BenchLM mirrors the published ioi score view for IOI. GPT-5.6 Sol leads the public snapshot at 86.67% , followed by GPT-5.6 Luna (72.92%) and Claude Fable 5 (72.25%). BenchLM does not use these results to rank models overall.

1

GPT-5.6 Sol

OpenAI

openai/gpt-5.6-sol

86.67%
Overall —
2

GPT-5.6 Luna

OpenAI

openai/gpt-5.6-luna

72.92%
Overall —
3

Claude Fable 5

Anthropic

anthropic/claude-fable-5

72.25%
Overall —
58 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 9, 2026

The published IOI snapshot is tightly clustered at the top: GPT-5.6 Sol sits at 86.67%, while the third row is only 14.42 points behind. The broader top-10 spread is 47.58 points, so the benchmark still separates strong models even when the leaders cluster.

58 models have been evaluated on IOI. The benchmark falls in the External benchmark mirrors category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. IOI is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About IOI

Year

2026

Tasks

International Olympiad in Informatics-style programming tasks

Format

Accuracy score

Difficulty

Olympiad programming

BenchLM mirrors the public Vals AI IOI leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

IOIPublic benchmark source

BenchLM freshness & provenance

Version

IOI 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

IOI score table (58 models)

1
GPT-5.6 Solopenai/gpt-5.6-sol
86.67%
2
GPT-5.6 Lunaopenai/gpt-5.6-luna
72.92%
3
Claude Fable 5anthropic/claude-fable-5
72.25%
4
GPT-5.4openai/gpt-5.4-2026-03-05
67.83%
5
GPT-5.6 Terraopenai/gpt-5.6-terra
65.25%
6
GPT-5.2openai/gpt-5.2-2025-12-11
54.83%
7
Claude Opus 4.7anthropic/claude-opus-4-7
47.08%
8
Qwen3.7 Maxalibaba/qwen3.7-max
46.75%
9
GPT-5.3 Codexopenai/gpt-5.3-codex
43.83%
10
Gemini 3 Flash Previewgoogle/gemini-3-flash-preview
39.08%
11
Gemini 3 Pro Previewgoogle/gemini-3-pro-preview
38.83%
12
DeepSeek V4 Prodeepseek/deepseek-v4-pro
35.83%
13
Grok 4.20 0309 Reasoninggrok/grok-4.20-0309-reasoning
30.17%
14
Grok 4 0709grok/grok-4-0709
26.17%
15
Claude Opus 4.5anthropic/claude-opus-4-5-20251101
23.58%
16
GLM 5 Thinkingzai/glm-5-thinking
22.00%
17
GPT-5.1openai/gpt-5.1-2025-11-13
21.50%
18
GPT-5.1 Codex Maxopenai/gpt-5.1-codex-max
21.42%
19
Claude Opus 4.5 20251101 Thinkinganthropic/claude-opus-4-5-20251101-thinking
20.25%
20
GPT-5openai/gpt-5-2025-08-07
20.00%
21
Claude Sonnet 4.5 20250929 Thinkinganthropic/claude-sonnet-4-5-20250929-thinking
18.33%
22
Kimi K2.5 Thinkingkimi/kimi-k2.5-thinking
17.67%
23
Gemini 2.5 Progoogle/gemini-2.5-pro
17.08%
24
Qwen3 Maxalibaba/qwen3-max
15.67%
25
Grok 4.3grok/grok-4.3
15.33%
26
GPT-5.4 Nanoopenai/gpt-5.4-nano-2026-03-17
15.25%
27
DeepSeek V3p2fireworks/deepseek-v3p2
14.42%
28
Qwen3 Maxalibaba/qwen3-max-2026-01-23
13.75%
29
Claude Opus 4.1anthropic/claude-opus-4-1-20250805
12.52%
30
Grok 4 Fast Reasoninggrok/grok-4-fast-reasoning
11.50%
31
DeepSeek V3p2 Thinkingfireworks/deepseek-v3p2-thinking
10.67%
32
GPT-5 Codexopenai/gpt-5-codex
9.75%
33
Qwen3 Max Previewalibaba/qwen3-max-preview
7.75%
34
Grok 4.1 Fast Non Reasoninggrok/grok-4-1-fast-non-reasoning
7.67%
35
GLM 4.7zai/glm-4.7
7.58%
36
GPT-5 Miniopenai/gpt-5-mini-2025-08-07
6.75%
37
MiniMax M2.5minimax/MiniMax-M2.5
6.67%
38
Claude Sonnet 4anthropic/claude-sonnet-4-20250514
6.50%
39
GPT-5.4 Miniopenai/gpt-5.4-mini-2026-03-17
6.42%
40
Claude Haiku 4.5 20251001 Thinkinganthropic/claude-haiku-4-5-20251001-thinking
6.17%
41
MiniMax M2.7minimax/MiniMax-M2.7
4.92%
42
O4 Miniopenai/o4-mini-2025-04-16
4.83%
43
Claude Sonnet 4 20250514 Thinkinganthropic/claude-sonnet-4-20250514-thinking
4.58%
44
GLM 4.6zai/glm-4.6
4.33%
45
Grok Code Fast 1grok/grok-code-fast-1
4.33%
46
Mistral Large 2512mistralai/mistral-large-2512
4.00%
47
Grok 4 Fast Non Reasoninggrok/grok-4-fast-non-reasoning
3.83%
48
GPT-5.1 Codexopenai/gpt-5.1-codex
3.67%
49
Grok 4.1 Fast Reasoninggrok/grok-4-1-fast-reasoning
3.08%
50
GLM 4.5zai/glm-4.5
2.92%
51
Gemini 2.5 Flashgoogle/gemini-2.5-flash
2.61%
52
Labs Devstral Small 2512mistralai/labs-devstral-small-2512
2.50%
53
MiniMax M2.1minimax/MiniMax-M2.1
2.33%
54
DeepSeek V3 0324fireworks/deepseek-v3-0324
1.67%
55
Moonshotai Kimi K2 Instructtogether/moonshotai/Kimi-K2-Instruct
1.25%
56
Magistral Medium 2509mistralai/magistral-medium-2509
0.67%
57
Devstral 2512mistralai/devstral-2512
0.67%
58
Qwen3 235b A22bfireworks/qwen3-235b-a22b
0.00%

FAQ

What does IOI measure?

Based on the International Olympiad in Informatics

Which model leads the published IOI snapshot?

GPT-5.6 Sol currently leads the published IOI snapshot with 86.67% ioi score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on IOI?

58 AI models are included in BenchLM's mirrored IOI snapshot, based on the public leaderboard captured on July 9, 2026.

Last updated: July 9, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.