Inference
EN
Vals AI

IOI v1

Based on the International Olympiad in Informatics

ModelsModels with a result.60
Top resultBest result on this benchmark.91.7%Claude Opus 5
Top-3 spreadPoints from first to third.18.7 pts
UpdatedDate the source changed the results.9 Aug 2026

Result and cost

61 of 61 results

Results

61 results
#ModelResultThe score from the source.CostUS dollars to run one task.TimeTime to run one task.
01Claude Opus 591.7% ±8.3$5.5428 min
02GPT-5.6 Sol86.7% ±1.7$2.9922 min
03Qwen3.8 Max73.0% ±1.0$2.3966 min
04GPT-5.6 Luna72.9% ±5.1$0.26328 min
05Claude Fable 572.3% ±9.4$15.1055 min
06GPT-5.467.8% ±9.9$3.4744 min
07GPT-5.6 Terra65.3% ±0.9$0.97422 min
08GPT-5.254.8% ±8.3$3.871.9 h
09Muse Spark 1.249.5% ±3.7$6.1080 min
10Claude Opus 4.747.1% ±8.7$10.4951 min
11Qwen3.7 Max46.8% ±10.3$4.8673 min
12GPT-5.3 Codex43.8% ±7.8$2.0260 min
13Gemini 3 Flash Preview39.1% ±10.5$0.37531 min
14Gemini 3 Pro38.8% ±11.5$0.33115 min
15DeepSeek V4 Pro 042335.8% ±7.1$0.56990 min
16Grok 4.20 (Reasoning)30.2% ±7.5$0.70915 min
17Gemini 3.5 Flash-Lite26.2% ±1.2$0.63615 min
17Grok 426.2% ±6.8$2.6971 min
19Claude Opus 4.523.6% ±7.5$3.052.1 h
20GLM-5 Thinking22.0% ±7.8$3.271.9 h
21GPT-5.121.5% ±7.3$0.36829 min
22GPT-5.1-Codex-Max21.4% ±7.0$0.42316 min
23Claude Opus 4.5 Thinking20.3% ±5.2$3.922.3 h
24GPT-520.0% ±4.6$1.6343 min
25Claude Sonnet 4.5 Thinking18.3% ±5.9$3.0755 min
26Kimi K2.5 Thinking17.7% ±6.1$0.67764 min
27Gemini 2.5 Pro17.1% ±6.2$0.61549 min
28Qwen3 Maxqwen3-max15.7% ±6.4$0.82534 min
29Grok 4.315.3% ±6.3$0.35210 min
29GPT-5.4 nano15.3% ±6.4$0.04320 min
31DeepSeek V3.214.4% ±4.5$0.05240 min
32Claude Opus 4.112.5% ±4.9$17.591.7 h
33Grok 4 Fast (Reasoning)11.5% ±4.4$0.97423 min
34DeepSeek V3.2 (Thinking)10.7% ±3.1$0.05926 min
35GPT-5 Codex9.8% ±7.7$2.6726 min
36Qwen3 Maxqwen3-max-preview7.8% ±3.2$1.4056 min
37Grok 4.1 Fast Non Reasoning7.7% ±3.2$0.072.1 h
38GLM-4.77.6% ±3.4$0.44489 min
39GPT-5 mini6.8% ±3.3$0.0397 min
40MiniMax M2.56.7% ±2.6$1.506.4 h
41Claude Sonnet 46.5% ±2.1$2.3954 min
42GPT-5.4 mini6.4% ±3.6$0.35132 min
43Claude Haiku 4.5 Thinking6.2% ±2.5$2.132.1 h
44MiniMax M2.74.9% ±2.4$1.1554 min
45o4-mini4.8% ±2.4$0.1568 min
46Claude Sonnet 4 Thinking4.6% ±1.1$1.3337 min
47GLM-4.64.3% ±2.5$1.522.0 h
47Grok Code Fast 14.3% ±1.2$1.6218 min
49Mistral Large 34.0% ±1.5$3.071.9 h
50Grok 4 Fast Non Reasoning3.8% ±2.8$0.12710 min
51GPT-5.1-Codex3.7% ±3.3$0.17737 min
52Grok 4.1 Fast (Reasoning)3.1% ±1.7$0.0326 min
53GLM-4.52.9% ±1.0$0.94239 min
54Gemini 2.5 Flash2.6% ±1.0$0.0376 min
55Labs Devstral Small2.5% ±1.8$0.5062.1 h
56MiniMax M2.12.3% ±1.3$0.31987 min
57DeepSeek V3 03241.7% ±0.9$0.6063 min
58Kimi K2 Instruct1.3% ±0.6$2.3726 min
59Magistral Medium0.7% ±0.4$6.3437 min
59Devstral 2 25120.7% ±0.6$1.752.2 h
61Qwen3 235B-A22B0.0%$0.116 min