# IOI / ioi2025 > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025. Based on the International Olympiad in Informatics Canonical URL: https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025 Last updated: Wed, 21 Oct 2026 18:05:10 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Conquered Based on the International Olympiad in Informatics Coding · Models tested: 29 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 100% | SE ±0 pp | $5.11 | 1,562.49source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.113398 \| USD \| per_test \| Lower is better \| \| `latency` \| 1562.492 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 44 stderr 0 tokenTotals {"cache_read_tokens":1910090,"cache_write_tokens":180790,"input_tokens":2091102,"output_tokens":70089,"reasoning_tokens":38414} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-6-astra` | | | | | | | | 1 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 100% | SE ±0 pp | $0.81 | 1,321.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.813679 \| USD \| per_test \| Lower is better \| \| `latency` \| 1321.855 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 44 stderr 0 tokenTotals {"cache_read_tokens":1808231,"cache_write_tokens":212015,"input_tokens":2020492,"output_tokens":79067,"reasoning_tokens":45902} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-6.1-sol` | | | | | | | | 1 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 100% | SE ±0 pp | $2.88 | 1,034.5source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.880431 \| USD \| per_test \| Lower is better \| \| `latency` \| 1034.504 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 44 stderr 0 tokenTotals {"cache_read_tokens":17488090,"cache_write_tokens":0,"input_tokens":18679947,"output_tokens":450877,"reasoning_tokens":288219} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-4-argon Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/google~1gemini-4-argon` | | | | | | | | 1 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 100% | SE ±0 pp | $3.06 | 441.46source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.061283 \| USD \| per_test \| Lower is better \| \| `latency` \| 441.464 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 44 stderr 0 tokenTotals {"cache_read_tokens":12994777,"cache_write_tokens":644000,"input_tokens":13639029,"output_tokens":497439,"reasoning_tokens":409486} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/anthropic~1claude-opus-5-5` | | | | | | | | 5 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 88.33% | SE ±10.65 pp | $8.93 | 3,965.79source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.93332 \| USD \| per_test \| Lower is better \| \| `latency` \| 3965.785 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10.65 pp sourcePopulation 44 stderr 10.65 tokenTotals {"cache_read_tokens":4977405,"cache_write_tokens":637272,"input_tokens":5615082,"output_tokens":205890,"reasoning_tokens":160719} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-5.6-sol Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-5.6-sol` | | | | | | | | 5 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 88.33% | SE ±10.65 pp | $4.61 | 1,746.18source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.613218 \| USD \| per_test \| Lower is better \| \| `latency` \| 1746.178 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10.65 pp sourcePopulation 44 stderr 10.65 tokenTotals {"cache_read_tokens":48266419,"cache_write_tokens":2040622,"input_tokens":50307537,"output_tokens":1282221,"reasoning_tokens":1122840} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/anthropic~1claude-sonnet-5-5` | | | | | | | | 7 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 87.17% | SE ±11.72 pp | $16.52 | 3,406.43source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.167 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 16.518293 \| USD \| per_test \| Lower is better \| \| `latency` \| 3406.434 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±11.72 pp sourcePopulation 44 stderr 11.715 tokenTotals {"cache_read_tokens":94974943,"cache_write_tokens":2613707,"input_tokens":97589394,"output_tokens":1411316,"reasoning_tokens":1151620} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/anthropic~1claude-opus-5` | | | | | | | | 7 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 87.17% | SE ±11.72 pp | $12.52 | 2,233.03source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.167 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 12.516821 \| USD \| per_test \| Lower is better \| \| `latency` \| 2233.026 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±11.72 pp sourcePopulation 44 stderr 11.715 tokenTotals {"cache_read_tokens":39288242,"cache_write_tokens":1699728,"input_tokens":40988406,"output_tokens":1183945,"reasoning_tokens":1034144} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/anthropic~1claude-fable-5-1` | | | | | | | | 9 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 79.33% | SE ±11.93 pp | $3.36 | 1,975.57source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.361427 \| USD \| per_test \| Lower is better \| \| `latency` \| 1975.572 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±11.93 pp sourcePopulation 44 stderr 11.934 tokenTotals {"cache_read_tokens":4091306,"cache_write_tokens":408977,"input_tokens":4500601,"output_tokens":127414,"reasoning_tokens":98238} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-6-sol Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-6-sol` | | | | | | | | 10 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 77.83% | SE ±12.82 pp | $9.88 | 4,635.84source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.87522 \| USD \| per_test \| Lower is better \| \| `latency` \| 4635.842 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±12.82 pp sourcePopulation 44 stderr 12.824 tokenTotals {"cache_read_tokens":7976676,"cache_write_tokens":478896,"input_tokens":8456064,"output_tokens":262603,"reasoning_tokens":224508} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-5.6-terra Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-5.6-terra` | | | | | | | | 11 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 75.5% | SE ±14.17 pp | $5.27 | 1,685.3source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.268373 \| USD \| per_test \| Lower is better \| \| `latency` \| 1685.297 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±14.17 pp sourcePopulation 44 stderr 14.169 tokenTotals {"cache_read_tokens":47616340,"cache_write_tokens":0,"input_tokens":48683200,"output_tokens":877281,"reasoning_tokens":718587} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label meta/muse-wonder Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/meta~1muse-wonder` | | | | | | | | 12 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 69.83% | SE ±15.19 pp | $2.3 | 781.83source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.302837 \| USD \| per_test \| Lower is better \| \| `latency` \| 781.833 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±15.19 pp sourcePopulation 44 stderr 15.185 tokenTotals {"cache_read_tokens":29768080,"cache_write_tokens":0,"input_tokens":33069022,"output_tokens":586720,"reasoning_tokens":334266} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-3.7-flash Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/google~1gemini-3.7-flash` | | | | | | | | 13 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 61.33% | SE ±15.01 pp | $3.56 | 697.5source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.559997 \| USD \| per_test \| Lower is better \| \| `latency` \| 697.499 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±15.01 pp sourcePopulation 44 stderr 15.01 tokenTotals {"cache_read_tokens":68238407,"cache_write_tokens":0,"input_tokens":71610674,"output_tokens":808776,"reasoning_tokens":576185} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-3.8-flash Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/google~1gemini-3.8-flash` | | | | | | | | 14 | [GPT-5.3 Codex](https://benchize.com/models/gpt-5-3-codex-xhigh.md)Extra high | 57% | SE ±15.45 pp | $2.17 | 1,321.09source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.174323 \| USD \| per_test \| Lower is better \| \| `latency` \| 1321.093 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±15.45 pp sourcePopulation 44 stderr 15.452 tokenTotals {"cache_read_tokens":17182208,"cache_write_tokens":0,"input_tokens":18182442,"output_tokens":592046,"reasoning_tokens":451657} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-5.3-codex Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-5.3-codex` | | | | | | | | 15 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 54.17% | SE ±12.55 pp | $0.26 | 7,184.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.167 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.256024 \| USD \| per_test \| Lower is better \| \| `latency` \| 7184.077 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±12.55 pp sourcePopulation 44 stderr 12.553 tokenTotals {"cache_read_tokens":163619392,"cache_write_tokens":0,"input_tokens":166224962,"output_tokens":1477004,"reasoning_tokens":1272448} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label xiaomi/mimo-v2.6-flash Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/xiaomi~1mimo-v2.6-flash` | | | | | | | | 16 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 49.83% | SE ±15.45 pp | $0.54 | 4,248.96source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.543819 \| USD \| per_test \| Lower is better \| \| `latency` \| 4248.955 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±15.45 pp sourcePopulation 44 stderr 15.446 tokenTotals {"cache_read_tokens":54119432,"cache_write_tokens":1016865,"input_tokens":55137587,"output_tokens":489046,"reasoning_tokens":356631} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-5.6-luna Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-5.6-luna` | | | | | | | | 16 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 49.83% | SE ±17.72 pp | $2.29 | 5,117.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.286536 \| USD \| per_test \| Lower is better \| \| `latency` \| 5117.861 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 1024000 provider Stepfun reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±17.72 pp sourcePopulation 44 stderr 17.718 tokenTotals {"cache_read_tokens":106455808,"cache_write_tokens":0,"input_tokens":109078778,"output_tokens":1669504,"reasoning_tokens":0} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label stepfun/step-5-preview Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/stepfun~1step-5-preview` | | | | | | | | 18 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 48.5% | SE ±14.04 pp | $2.62 | 6,167.41source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.620016 \| USD \| per_test \| Lower is better \| \| `latency` \| 6167.407 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±14.04 pp sourcePopulation 44 stderr 14.041 tokenTotals {"cache_read_tokens":161448832,"cache_write_tokens":0,"input_tokens":161838645,"output_tokens":2026899,"reasoning_tokens":1719775} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 19 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 46.83% | SE ±13.18 pp | $1.41 | 917.1source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.414465 \| USD \| per_test \| Lower is better \| \| `latency` \| 917.103 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±13.18 pp sourcePopulation 44 stderr 13.181 tokenTotals {"cache_read_tokens":6508383,"cache_write_tokens":0,"input_tokens":7930164,"output_tokens":361796,"reasoning_tokens":298868} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-3.1-pro-preview Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/google~1gemini-3.1-pro-preview` | | | | | | | | 19 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-xhigh.md)Extra high | 46.83% | SE ±13.39 pp | $2.45 | 2,243.31source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.451039 \| USD \| per_test \| Lower is better \| \| `latency` \| 2243.31 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±13.39 pp sourcePopulation 44 stderr 13.386 tokenTotals {"cache_read_tokens":23369084,"cache_write_tokens":0,"input_tokens":24665482,"output_tokens":2228922,"reasoning_tokens":2115096} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label meta/muse_spark_1_3 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/meta~1muse_spark_1_3` | | | | | | | | 21 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 42% | SE ±15.19 pp | $14.81 | 4,427.24source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 14.811094 \| USD \| per_test \| Lower is better \| \| `latency` \| 4427.238 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±15.19 pp sourcePopulation 44 stderr 15.19 tokenTotals {"cache_read_tokens":245792345,"cache_write_tokens":6241633,"input_tokens":252035458,"output_tokens":2410105,"reasoning_tokens":2121726} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label anthropic/claude-sonnet-5 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/anthropic~1claude-sonnet-5` | | | | | | | | 22 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 40.83% | SE ±9.71 pp | $1.75 | 935.62source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.747464 \| USD \| per_test \| Lower is better \| \| `latency` \| 935.617 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.71 pp sourcePopulation 44 stderr 9.711 tokenTotals {"cache_read_tokens":20352477,"cache_write_tokens":0,"input_tokens":22669003,"output_tokens":527617,"reasoning_tokens":382252} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/google~1gemini-3.6-flash` | | | | | | | | 23 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 39.33% | SE ±18.07 pp | $1.15 | 13,526.41source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.154221 \| USD \| per_test \| Lower is better \| \| `latency` \| 13526.414 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±18.07 pp sourcePopulation 44 stderr 18.072 tokenTotals {"cache_read_tokens":61284224,"cache_write_tokens":0,"input_tokens":65737574,"output_tokens":3554858,"reasoning_tokens":3491200} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label xiaomi/mimo-v2.6-pro Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/xiaomi~1mimo-v2.6-pro` | | | | | | | | 24 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 39% | SE ±17.41 pp | $0.16 | 1,692.64source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.155148 \| USD \| per_test \| Lower is better \| \| `latency` \| 1692.641 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±17.41 pp sourcePopulation 44 stderr 17.408 tokenTotals {"cache_read_tokens":17298254,"cache_write_tokens":863717,"input_tokens":18162547,"output_tokens":604036,"reasoning_tokens":548590} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-6-luna Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-6-luna` | | | | | | | | 25 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 35.17% | SE ±9.18 pp | $0.3 | 1,631.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.167 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.297858 \| USD \| per_test \| Lower is better \| \| `latency` \| 1631.199 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.18 pp sourcePopulation 44 stderr 9.182 tokenTotals {"cache_read_tokens":51142912,"cache_write_tokens":0,"input_tokens":51333215,"output_tokens":1169612,"reasoning_tokens":1027911} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/deepseek~1deepseek-v4.1-flash` | | | | | | | | 26 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 31.33% | SE ±14.52 pp | $1.22 | 1,109.98source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.222573 \| USD \| per_test \| Lower is better \| \| `latency` \| 1109.984 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±14.52 pp sourcePopulation 44 stderr 14.521 tokenTotals {"cache_read_tokens":45957889,"cache_write_tokens":2624882,"input_tokens":48583121,"output_tokens":1989749,"reasoning_tokens":1843916} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/anthropic~1claude-haiku-5-5` | | | | | | | | 27 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 28.17% | SE ±10.33 pp | $0.38 | 1,580.14source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.167 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.381691 \| USD \| per_test \| Lower is better \| \| `latency` \| 1580.139 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 256000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10.33 pp sourcePopulation 44 stderr 10.326 tokenTotals {"cache_read_tokens":49070848,"cache_write_tokens":0,"input_tokens":49247535,"output_tokens":1134860,"reasoning_tokens":981192} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label deepseek/deepseek-v4-flash-0731 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/deepseek~1deepseek-v4-flash-0731` | | | | | | | | 28 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 23.17% | SE ±10.34 pp | $3.88 | 2,103.37source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 23.167 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.879691 \| USD \| per_test \| Lower is better \| \| `latency` \| 2103.366 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10.34 pp sourcePopulation 44 stderr 10.34 tokenTotals {"cache_read_tokens":95167310,"cache_write_tokens":0,"input_tokens":97687063,"output_tokens":1350840,"reasoning_tokens":1026584} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label meta/muse_spark_1_2 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/meta~1muse_spark_1_2` | | | | | | | | 29 | [Mercury 2.5](https://benchize.com/models/mercury-2-5-high.md)High | 3.5% | SE ±2.69 pp | $0.19 | 239.92source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 3.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.187303 \| USD \| per_test \| Lower is better \| \| `latency` \| 239.919 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Inception reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.69 pp sourcePopulation 44 stderr 2.685 tokenTotals {"cache_read_tokens":7109497,"cache_write_tokens":0,"input_tokens":11283658,"output_tokens":173264,"reasoning_tokens":165909} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label inception/mercury-2.5 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/inception~1mercury-2.5` | | | | | | | --- Cite as: IOI / ioi2025 — Benchize, https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025 (retrieved 2026-10-21)