Skip to main content
BenchLM
Advertise

Benchmark profile

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 23, 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.

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

IOI score on IOI — July 23, 2026

BenchLM mirrors the published ioi score view for IOI. Claude Opus 5 leads the public snapshot at 91.67% , followed by GPT-5.6 Sol (86.67%) and GPT-5.6 Luna (72.92%). BenchLM does not use these results to rank models overall.

1

Claude Opus 5

Anthropic

anthropic/claude-opus-5

91.67%
Overall —
2

GPT-5.6 Sol

OpenAI

openai/gpt-5.6-sol

86.67%
Overall —
3

GPT-5.6 Luna

OpenAI

openai/gpt-5.6-luna

72.92%
Overall —
60 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 23, 2026

IOI score table (60 models)

Score
1
Claude Opus 5Anthropic
91.67%
2
GPT-5.6 SolOpenAI
86.67%
3
GPT-5.6 LunaOpenAI
72.92%
4
Claude Fable 5Anthropic
72.25%
5
GPT-5.4OpenAI
67.83%
6
GPT-5.6 TerraOpenAI
65.25%
7
GPT-5.2OpenAI
54.83%
8
Claude Opus 4.7Anthropic
47.08%
9
Qwen3.7 MaxAlibaba
46.75%
10
GPT-5.3 CodexOpenAI
43.83%
11
Gemini 3 Flash PreviewGoogle
39.08%
12
Gemini 3 Pro PreviewGoogle
38.83%
13
DeepSeek V4 ProDeepSeek
35.83%
14
Grok 4.20 0309 ReasoningxAI
30.17%
15
Gemini 3.5 Flash LiteGoogle
26.17%
16
Grok 4 0709xAI
26.17%
17
Claude Opus 4.5Anthropic
23.58%
18
GLM 5 ThinkingZhipu AI
22.00%
19
GPT-5.1OpenAI
21.50%
20
GPT-5.1 Codex MaxOpenAI
21.42%
21
Claude Opus 4.5 20251101 ThinkingAnthropic
20.25%
22
GPT-5OpenAI
20.00%
23
Claude Sonnet 4.5 20250929 ThinkingAnthropic
18.33%
24
Kimi K2.5 ThinkingMoonshot AI
17.67%
25
Gemini 2.5 ProGoogle
17.08%
26
Qwen3 MaxAlibaba
15.67%
27
Grok 4.3xAI
15.33%
28
GPT-5.4 NanoOpenAI
15.25%
29
DeepSeek V3p2Fireworks AI
14.42%
30
Qwen3 MaxAlibaba
13.75%
31
Claude Opus 4.1Anthropic
12.52%
32
Grok 4 Fast ReasoningxAI
11.50%
33
DeepSeek V3p2 ThinkingFireworks AI
10.67%
34
GPT-5 CodexOpenAI
9.75%
35
Qwen3 Max PreviewAlibaba
7.75%
36
Grok 4.1 Fast Non ReasoningxAI
7.67%
37
GLM 4.7Zhipu AI
7.58%
38
GPT-5 MiniOpenAI
6.75%
39
MiniMax M2.5MiniMax
6.67%
40
Claude Sonnet 4Anthropic
6.50%
41
GPT-5.4 MiniOpenAI
6.42%
42
Claude Haiku 4.5 20251001 ThinkingAnthropic
6.17%
43
MiniMax M2.7MiniMax
4.92%
44
O4 MiniOpenAI
4.83%
45
Claude Sonnet 4 20250514 ThinkingAnthropic
4.58%
46
GLM 4.6Zhipu AI
4.33%
47
Grok Code Fast 1xAI
4.33%
48
Mistral Large 2512Mistral AI
4.00%
49
Grok 4 Fast Non ReasoningxAI
3.83%
50
GPT-5.1 CodexOpenAI
3.67%
51
Grok 4.1 Fast ReasoningxAI
3.08%
52
GLM 4.5Zhipu AI
2.92%
53
Gemini 2.5 FlashGoogle
2.61%
54
Labs Devstral Small 2512Mistral AI
2.50%
55
MiniMax M2.1MiniMax
2.33%
56
DeepSeek V3 0324Fireworks AI
1.67%
57
Moonshotai Kimi K2 InstructTogether AI
1.25%
58
Magistral Medium 2509Mistral AI
0.67%
59
Devstral 2512Mistral AI
0.67%
60
Qwen3 235b A22bFireworks AI
0.00%

The published IOI snapshot places Claude Opus 5 first at 91.67%. The third row is 18.75 points behind. The broader top-10 range is 47.83 points, so the table still separates the published systems.

60 models have been evaluated on IOI. The benchmark falls in the External benchmark mirrors category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. 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.

FAQ

What does IOI measure?

Based on the International Olympiad in Informatics

Which model leads the published IOI snapshot?

Claude Opus 5 currently leads the published IOI snapshot with 91.67% ioi score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on IOI?

60 AI models are included in BenchLM's mirrored IOI snapshot, based on the public leaderboard captured on July 23, 2026.

Last updated: July 23, 2026 · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.