# SWE-bench / >4 hours > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Aswebench%3A%3E4%20hours. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Aswebench%3A%3E4%20hours. Solving production software engineering tasks Canonical URL: https://benchize.com/benchmarks/vals-ai%3Aswebench%3A%3E4%20hours Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Conquered Solving production software engineering tasks Coding · Models tested: 39 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 100% | SE ±0 pp | $1.9 | 1,206.14source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.895371 \| USD \| per_test \| Lower is better \| \| `latency` \| 1206.142 \| 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 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label openai/gpt-5.6-sol Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/openai~1gpt-5.6-sol` | | | | | | | | 1 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 100% | SE ±0 pp | $2.24 | 1,052.44source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.240184 \| USD \| per_test \| Lower is better \| \| `latency` \| 1052.442 \| 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 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-fable-5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/anthropic~1claude-fable-5` | | | | | | | | 1 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 100% | SE ±0 pp | $0.3 | 589.87source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.302705 \| USD \| per_test \| Lower is better \| \| `latency` \| 589.874 \| 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: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 1 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 100% | SE ±0 pp | $0.55 | 269.94source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.550043 \| USD \| per_test \| Lower is better \| \| `latency` \| 269.938 \| 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 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label openai/gpt-5.6-terra Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/openai~1gpt-5.6-terra` | | | | | | | | 1 | [Claude Opus 5](https://benchize.com/models/claude-opus-5.md) | 100% | SE ±0 pp | $3.42 | 2,224.45source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.416648 \| USD \| per_test \| Lower is better \| \| `latency` \| 2224.447 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/anthropic~1claude-opus-5` | | | | | | | | 6 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 66.67% | SE ±33.33 pp | $1.51 | 479.33source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.509878 \| USD \| per_test \| Lower is better \| \| `latency` \| 479.329 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/openai~1gpt-5.5` | | | | | | | | 6 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 66.67% | SE ±33.33 pp | $0.68 | 518.43source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.676282 \| USD \| per_test \| Lower is better \| \| `latency` \| 518.434 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 256000 provider Meta reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label meta/muse_spark_1_1 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/meta~1muse_spark_1_1` | | | | | | | | 6 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 66.67% | SE ±33.33 pp | $0.15 | 417.31source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.145928 \| USD \| per_test \| Lower is better \| \| `latency` \| 417.313 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label openai/gpt-5.6-luna Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/openai~1gpt-5.6-luna` | | | | | | | | 6 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 66.67% | SE ±33.33 pp | $5.42 | 1,170.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.416409 \| USD \| per_test \| Lower is better \| \| `latency` \| 1170.395 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-opus-4-7 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/anthropic~1claude-opus-4-7` | | | | | | | | 6 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 66.67% | SE ±33.33 pp | $3.17 | 1,263.34source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.172757 \| USD \| per_test \| Lower is better \| \| `latency` \| 1263.337 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-opus-4-8 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/anthropic~1claude-opus-4-8` | | | | | | | | 6 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 66.67% | SE ±33.33 pp | $3.54 | 2,127.31source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.544588 \| USD \| per_test \| Lower is better \| \| `latency` \| 2127.307 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-sonnet-5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/anthropic~1claude-sonnet-5` | | | | | | | | 6 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 66.67% | SE ±33.33 pp | $0.02 | 343.14source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.01512 \| USD \| per_test \| Lower is better \| \| `latency` \| 343.144 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label deepseek/deepseek-v4-flash-0731 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/deepseek~1deepseek-v4-flash-0731` | | | | | | | | 13 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 33.33% | SE ±33.33 pp | $2.75 | 634.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.747013 \| USD \| per_test \| Lower is better \| \| `latency` \| 634.863 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-3.7-flash Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-3.7-flash` | | | | | | | | 13 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 33.33% | SE ±33.33 pp | $1.03 | 424.84source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.025173 \| USD \| per_test \| Lower is better \| \| `latency` \| 424.841 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-3.1-pro-preview Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-3.1-pro-preview` | | | | | | | | 13 | [Mistral Large 3 2512](https://benchize.com/models/mistral-large-2512.md) | 33.33% | SE ±33.33 pp | $0.51 | 221.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.507432 \| USD \| per_test \| Lower is better \| \| `latency` \| 221.861 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 256000 provider Mistral AI reasoning Not reported Reasoning effort unknown Temperature 0.065 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label mistralai/mistral-large-2512 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/mistralai~1mistral-large-2512` | | | | | | | | 13 | [MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md) | 33.33% | SE ±33.33 pp | $0.64 | 548.62source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.644463 \| USD \| per_test \| Lower is better \| \| `latency` \| 548.617 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 196608 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label minimax/MiniMax-M2.5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/minimax~1MiniMax-M2.5` | | | | | | | | 13 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 33.33% | SE ±33.33 pp | $0.35 | 366source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.349943 \| USD \| per_test \| Lower is better \| \| `latency` \| 365.995 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-3-flash-preview Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-3-flash-preview` | | | | | | | | 13 | [Nemotron 3 Ultra](https://benchize.com/models/nemotron-3-ultra-550b-a55b.md) | 33.33% | SE ±33.33 pp | — | 475.33source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `latency` \| 475.334 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Nvidia reasoning Not reported Reasoning effort unknown Temperature Not reported topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label nvidia/nemotron-3-ultra-550b-a55b Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/nvidia~1nemotron-3-ultra-550b-a55b` | | | | | | | | 13 | [GPT-5.2 Codex](https://benchize.com/models/gpt-5-2-codex-high.md)High | 33.33% | SE ±33.33 pp | $0.51 | 268.27source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.510369 \| USD \| per_test \| Lower is better \| \| `latency` \| 268.266 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label openai/gpt-5.2-codex Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/openai~1gpt-5.2-codex` | | | | | | | | 13 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 33.33% | SE ±33.33 pp | $1.12 | 983.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.124392 \| USD \| per_test \| Lower is better \| \| `latency` \| 983.756 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label meta/muse_spark_1_2 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/meta~1muse_spark_1_2` | | | | | | | | 13 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 33.33% | SE ±33.33 pp | $6.5 | 2,504.15source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.502794 \| USD \| per_test \| Lower is better \| \| `latency` \| 2504.149 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 80000 provider Mistral AI reasoning Not reported Reasoning effort high Temperature 0.7 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label mistralai/mistral-medium-3.5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/mistralai~1mistral-medium-3.5` | | | | | | | | 13 | [GPT-5.3 Codex](https://benchize.com/models/gpt-5-3-codex-xhigh.md)Extra high | 33.33% | SE ±33.33 pp | $0.7 | 412.1source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.69549 \| USD \| per_test \| Lower is better \| \| `latency` \| 412.097 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label openai/gpt-5.3-codex Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/openai~1gpt-5.3-codex` | | | | | | | | 13 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 33.33% | SE ±33.33 pp | $1.5 | 227.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.498598 \| USD \| per_test \| Lower is better \| \| `latency` \| 227.077 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-3.5-flash Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-3.5-flash` | | | | | | | | 13 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 33.33% | SE ±33.33 pp | $1.95 | 1,321.66source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.951118 \| USD \| per_test \| Lower is better \| \| `latency` \| 1321.655 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-3.6-flash` | | | | | | | | 13 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 33.33% | SE ±33.33 pp | $2.08 | 751.12source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.075859 \| USD \| per_test \| Lower is better \| \| `latency` \| 751.122 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/anthropic~1claude-sonnet-4-6` | | | | | | | | 13 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 33.33% | SE ±33.33 pp | $2.79 | 802.74source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.79018 \| USD \| per_test \| Lower is better \| \| `latency` \| 802.74 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-3.8-flash Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-3.8-flash` | | | | | | | | 13 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 33.33% | SE ±33.33 pp | $0.51 | 918.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.506961 \| USD \| per_test \| Lower is better \| \| `latency` \| 918.967 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 196608 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label minimax/MiniMax-M2.7 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/minimax~1MiniMax-M2.7` | | | | | | | | 13 | [MiniMax M2.1](https://benchize.com/models/minimax-m2-1.md) | 33.33% | SE ±33.33 pp | $0.82 | 650.54source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.817428 \| USD \| per_test \| Lower is better \| \| `latency` \| 650.542 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label minimax/MiniMax-M2.1 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/minimax~1MiniMax-M2.1` | | | | | | | | 13 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 33.33% | SE ±33.33 pp | $0.04 | 833.43source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.043185 \| USD \| per_test \| Lower is better \| \| `latency` \| 833.426 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label xiaomi/mimo-v2.5-pro Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/xiaomi~1mimo-v2.5-pro` | | | | | | | | 13 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 33.33% | SE ±33.33 pp | $0.41 | 822.7source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.413914 \| USD \| per_test \| Lower is better \| \| `latency` \| 822.702 \| 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: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-3.5-flash-lite Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-3.5-flash-lite` | | | | | | | | 13 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 33.33% | SE ±33.33 pp | $0.83 | 1,256.21source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.83109 \| USD \| per_test \| Lower is better \| \| `latency` \| 1256.214 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/minimax~1MiniMax-M3` | | | | | | | | 32 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 0% | SE ±0 pp | $1.23 | 486.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.226948 \| USD \| per_test \| Lower is better \| \| `latency` \| 486.969 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-2.5-pro Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-2.5-pro` | | | | | | | | 32 | [Command A](https://benchize.com/models/command-a.md) | 0% | SE ±0 pp | $0.08 | 1,068.02source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.084132 \| USD \| per_test \| Lower is better \| \| `latency` \| 1068.024 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 0.3 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label cohere/command-a-03-2025 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/cohere~1command-a-03-2025` | | | | | | | | 32 | [Laguna M 1](https://benchize.com/models/laguna-m-1.md) | 0% | SE ±0 pp | $0.58 | 1,139.61source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.583679 \| USD \| per_test \| Lower is better \| \| `latency` \| 1139.609 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 32768 provider Poolside reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label poolside/laguna-m.1 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/poolside~1laguna-m.1` | | | | | | | | 32 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-max.md)Max | 0% | SE ±0 pp | — | 893.87source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `latency` \| 893.873 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 256000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/deepseek~1deepseek-v4-pro` | | | | | | | | 32 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 0% | SE ±0 pp | $0.08 | 111.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.083345 \| USD \| per_test \| Lower is better \| \| `latency` \| 111.196 \| 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: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label google/gemini-3.1-flash-lite-preview Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 32 | [Devstral 2 2512](https://benchize.com/models/devstral-2512.md) | 0% | SE ±0 pp | $1.38 | 419.15source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.378311 \| USD \| per_test \| Lower is better \| \| `latency` \| 419.145 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 256000 provider Mistral AI reasoning Not reported Reasoning effort unknown Temperature 0.2 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label mistralai/devstral-2512 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/mistralai~1devstral-2512` | | | | | | | | 32 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 0% | SE ±0 pp | $0.02 | 507.37source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.015828 \| USD \| per_test \| Lower is better \| \| `latency` \| 507.374 \| 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: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label xiaomi/mimo-v2.5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/xiaomi~1mimo-v2.5` | | | | | | | | 32 | [Laguna Xs 2](https://benchize.com/models/laguna-xs-2.md) | 0% | SE ±0 pp | $0.25 | 340.49source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.24553 \| USD \| per_test \| Lower is better \| \| `latency` \| 340.489 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 32768 provider Poolside reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label poolside/laguna-xs.2 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/poolside~1laguna-xs.2` | | | | | | | --- Cite as: SWE-bench / >4 hours — Benchize, https://benchize.com/benchmarks/vals-ai%3Aswebench%3A%3E4%20hours (retrieved 2026-10-21)