English translation is being prepared.
Matched fieldsSummary、Body
←Search results
Search “DeepSeek”
English translation is being prepared.
Matched fieldsSummary、Body
English translation is being prepared.
Matched fieldsSummary、Body
Artificial Analysis ranks DeepSeek V4.1 Flash 1017 as the top open model
Artificial Analysis reports that Kimi K3.1 Pro scored 64% on the Artificial Analysis Cyber Index, ranking first among openly available models. The index consists of three benchmarks: CWE-Bench-AA, DeepsecBench-AA, and CyberGym-E2E-AA; K3.1 Pro scored 95% on CyberGym-E2E-AA, higher than GPT-6 Sol (Daybreak Blue)'s 93%. Its cost per task is $2.81, higher than GPT-6 Sol (Daybreak Blue, max)'s $1.77 and DeepSeek V4.1 Flash 1017's $0.42. Earlier the same day, Artificial Analysis ranked DeepSeek V4.1 Flash 1017 first among openly available models with a score of 57%, second on the overall leaderboard, 12 points behind GPT-6 Sol (69%), which is offered through a trusted access program; this version improved by 16 points over its predecessor DeepSeek V4.1 Flash's 41%, mainly due to CyberGym-E2E-AA rising from 23% to 76%.
Matched fieldsTitle
View story:Artificial Analysis says Kimi K3.1 Pro scores 64% on the Cyber Index
ARC Prize announces ARC-AGI verification results for DeepSeek V4.1 Flash 1017
ARC Prize announced the results of DeepSeek V4.1 Flash 1017 on the ARC-AGI validation set: a score of 78.1% on ARC-AGI-2 at a cost of $0.16 per task, and a score of 94.5% on ARC-AGI-1 at a cost of $0.06 per task. The organization also listed the changes in the best scores of the DeepSeek Flash series on ARC-AGI-2: V4 Flash 0731 at 61.4%, V4.1 Flash at 72.9%, and V4.1 Flash 1017 rising to 78.1%. A day earlier, Guillermo Rauch announced that Vercel would add DeepSeek v4.1 Flash (1017) to Token Pass, using DeepSeek's new weights, supporting a 1M context window with no configuration changes required; he said the model is fast, extremely low-priced, and offers zero data retention, making it suitable for running subagents for tasks planned by larger, more expensive models. Currently, the public information consists of the above results and the addition to Token Pass.
ARC Prize announced the results of DeepSeek V4.1 Flash 1017 on the ARC-AGI validation set: a score of 78.1% on ARC-AGI-2 at a cost of $0.16 per task, and a score of 94.5% on ARC-AGI-1 at a cost of $0.06 per task. The organization also listed the changes in the best scores of the DeepSeek Flash series on ARC-AGI-2: V4 Flash 0731 at 61.4%, V4.1 Flash at 72.9%, and V4.1 Flash 1017 rising to 78.1%. A day earlier, Guillermo Rauch announced that Vercel would add DeepSeek v4.1 Flash (1017) to Token Pas
Matched fieldsTitle
ARC Prize announces the ARC-AGI verified score of DeepSeek V4.1 Flash 1017
ARC Prize announced the results of DeepSeek V4.1 Flash 1017 on the ARC-AGI validation set: a score of 78.1% on ARC-AGI-2 at a cost of $0.16 per task, and a score of 94.5% on ARC-AGI-1 at a cost of $0.06 per task. The organization also listed the changes in the best scores of the DeepSeek Flash series on ARC-AGI-2: V4 Flash 0731 at 61.4%, V4.1 Flash at 72.9%, and V4.1 Flash 1017 rising to 78.1%. A day earlier, Guillermo Rauch announced that Vercel would add DeepSeek v4.1 Flash (1017) to Token Pass, using DeepSeek's new weights, supporting a 1M context window with no configuration changes required; he said the model is fast, extremely low-priced, and offers zero data retention, making it suitable for running subagents for tasks planned by larger, more expensive models. Currently, the public information consists of the above results and the addition to Token Pass.
Matched fieldsTitle
View story:ARC Prize announces ARC-AGI verification results for DeepSeek V4.1 Flash 1017
Fireworks AI publishes evaluation results of DeepSeek V4 Pro on CyberGym
On August 26, 2026, Fireworks AI published evaluation results of DeepSeek V4 Pro 0813 on the CyberGym security benchmark. The test covered 697 common valid tasks; DeepSeek V4 Pro's reward rate was 53.7%, with a cost of $2.502 per successful task, about half that of Kimi K3. In the same batch of results, Kimi K3 had the highest reward rate at 68.4%, with a cost of $4.914 per successful task; GPT-5.5 had a reward rate of 47.6%, with a cost of $9.641 per successful task; Claude Opus 4.8 had a reward rate of 5.9%, with a cost of $33.275 per successful task. Fireworks AI also said that DeepSeek V4 Pro produced native tool calls on all 840 tasks, with no refusals or output truncation; once it passed first-stage validation, its rate of completing the full patch was 94.7%. There are currently no further developments.
On August 26, 2026, Fireworks AI published evaluation results of DeepSeek V4 Pro 0813 on the CyberGym security benchmark. The test covered 697 common valid tasks; DeepSeek V4 Pro's reward rate was 53.7%, with a cost of $2.502 per successful task, about half that of Kimi K3. In the same batch of results, Kimi K3 had the highest reward rate at 68.4%, with a cost of $4.914 per successful task; GPT-5.5 had a reward rate of 47.6%, with a cost of $9.641 per successful task; Claude Opus 4.8 had a rewar
Matched fieldsTitle
Artificial Analysis Adds DeepSeek Search to Its Search Index Evaluation
Artificial Analysis has added DeepSeek Search to its search index evaluation. The evaluation results from October 22, 2026 show that DeepSeek Search scored 69 on the index, ranking 17th among 27 search products, and is the lowest-priced paid search API on the list: charging $0.75 per 1k searches, with a cost of about $0.032 per task, making it the 5th cheapest among the 27 products. In terms of accuracy, it scores 70% on AA-Omniscience, ranking 10th, but only 63% on BrowseComp, which requires multi-hop reasoning, ranking 25th. In addition, each search returns about 7k tokens, raising the model cost to the 2nd highest on the list. There are currently no further developments.
Artificial Analysis has added DeepSeek Search to its search index evaluation. The evaluation results from October 22, 2026 show that DeepSeek Search scored 69 on the index, ranking 17th among 27 search products, and is the lowest-priced paid search API on the list: charging $0.75 per 1k searches, with a cost of about $0.032 per task, making it the 5th cheapest among the 27 products. In terms of accuracy, it scores 70% on AA-Omniscience, ranking 10th, but only 63% on BrowseComp, which requires mu
Matched fieldsTitle
Artificial Analysis includes DeepSeek Search in its search index evaluation
Artificial Analysis has added DeepSeek Search to its search index evaluation. The evaluation results from October 22, 2026 show that DeepSeek Search scored 69 on the index, ranking 17th among 27 search products, and is the lowest-priced paid search API on the list: charging $0.75 per 1k searches, with a cost of about $0.032 per task, making it the 5th cheapest among the 27 products. In terms of accuracy, it scores 70% on AA-Omniscience, ranking 10th, but only 63% on BrowseComp, which requires multi-hop reasoning, ranking 25th. In addition, each search returns about 7k tokens, raising the model cost to the 2nd highest on the list. There are currently no further developments.
Matched fieldsTitle
View story:Artificial Analysis Adds DeepSeek Search to Its Search Index Evaluation
DeepSeek releases DeepSeek-V4.1-Flash-1017
On October 17, 2026, DeepSeek released DeepSeek-V4.1-Flash-1017, which the company says delivers stronger benchmark performance, faster task completion, and shorter outputs, achieving a Pareto improvement in performance and cost; it is now available on the official website, App, and API, and the model also launched on OpenRouter the same day. The company also announced that the Search and Fetch APIs are open to everyone, priced at $0.75 per 1,000 calls per endpoint, with calls made through server-side tools in DeepSeek Harness, Claude Code, and Codex temporarily free, and billing starting at 16:00 UTC on October 31, 2026. On October 17, Thomas Wolf commented that DeepSeek called this a "minor update," yet Terminal-Bench 4.0 rose from 31.2 to 42.3. On October 19, Arena announced that the model, with a score of 1670, became the highest-ranked open-source model on Code Arena: WebDev. On October 20, OpenCode updated it to version 1017 in Go and Free; Unsloth released a GGUF that can run locally, with the 1-bit quantized version retaining about 88.2% accuracy and shrinking in size from 508GB to 250GB; Arena then announced that it topped the Agent Arena open-source model leaderboard.
On October 17, 2026, DeepSeek released DeepSeek-V4.1-Flash-1017, which the company says delivers stronger benchmark performance, faster task completion, and shorter outputs, achieving a Pareto improvement in performance and cost; it is now available on the official website, App, and API, and the model also launched on OpenRouter the same day. The company also announced that the Search and Fetch APIs are open to everyone, priced at $0.75 per 1,000 calls per endpoint, with calls made through serve
Matched fieldsTitle
Arena announces DeepSeek-V4.1-Flash-1017 tops the Agent Arena open-source leaderboard
On October 17, 2026, DeepSeek released DeepSeek-V4.1-Flash-1017, which the company says delivers stronger benchmark performance, faster task completion, and shorter outputs, achieving a Pareto improvement in performance and cost; it is now available on the official website, App, and API, and the model also launched on OpenRouter the same day. The company also announced that the Search and Fetch APIs are open to everyone, priced at $0.75 per 1,000 calls per endpoint, with calls made through server-side tools in DeepSeek Harness, Claude Code, and Codex temporarily free, and billing starting at 16:00 UTC on October 31, 2026. On October 17, Thomas Wolf commented that DeepSeek called this a "minor update," yet Terminal-Bench 4.0 rose from 31.2 to 42.3. On October 19, Arena announced that the model, with a score of 1670, became the highest-ranked open-source model on Code Arena: WebDev. On October 20, OpenCode updated it to version 1017 in Go and Free; Unsloth released a GGUF that can run locally, with the 1-bit quantized version retaining about 88.2% accuracy and shrinking in size from 508GB to 250GB; Arena then announced that it topped the Agent Arena open-source model leaderboard.
Matched fieldsTitle
Arena announces DeepSeek-V4.1-Flash-1017 as the top open-source model on the Code Arena leaderboard
On October 17, 2026, DeepSeek released DeepSeek-V4.1-Flash-1017, which the company says delivers stronger benchmark performance, faster task completion, and shorter outputs, achieving a Pareto improvement in performance and cost; it is now available on the official website, App, and API, and the model also launched on OpenRouter the same day. The company also announced that the Search and Fetch APIs are open to everyone, priced at $0.75 per 1,000 calls per endpoint, with calls made through server-side tools in DeepSeek Harness, Claude Code, and Codex temporarily free, and billing starting at 16:00 UTC on October 31, 2026. On October 17, Thomas Wolf commented that DeepSeek called this a "minor update," yet Terminal-Bench 4.0 rose from 31.2 to 42.3. On October 19, Arena announced that the model, with a score of 1670, became the highest-ranked open-source model on Code Arena: WebDev. On October 20, OpenCode updated it to version 1017 in Go and Free; Unsloth released a GGUF that can run locally, with the 1-bit quantized version retaining about 88.2% accuracy and shrinking in size from 508GB to 250GB; Arena then announced that it topped the Agent Arena open-source model leaderboard.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle
Fireworks evaluates DeepSeek's new model
On September 14, 2026, Fireworks AI released and evaluated DeepSeek-V4.1-Flash. According to its published results, the model achieves 74.34% pass@1 on DeepSWE, on par with GPT-6-Astra's 74.12%; its cost per task is $0.43, about 1/15 that of Astra. The model is a 552B-parameter MoE, using separate activation budgets of 8B for input and 16B for output, and its KV Cache HBM footprint is reduced to 1/4 that of the previous-generation V4. On HLE it scores 34.52%, below Astra's 50.40%, and Fireworks considers it better suited to agentic coding than to highly difficult reasoning. On September 28, Fireworks AI released its first cache-aware router, FireRouter with Opus, which is now live in the CLI and offered for the first time as a standalone routing model; it can select among Claude Opus 5.5, GLM 5.3 and GLM 5.3 Flash based on task fit, prompt cache cost and switching cost; its internal A/B testing over more than a month showed coding task cost per session dropping from $15.36 to $6.63, a 57% reduction (±19 percentage points), with accuracy at pure O
On September 14, 2026, Fireworks AI released and evaluated DeepSeek-V4.1-Flash. According to its published results, the model achieves 74.34% pass@1 on DeepSWE, on par with GPT-6-Astra's 74.12%; its cost per task is $0.43, about 1/15 that of Astra. The model is a 552B-parameter MoE, using separate activation budgets of 8B for input and 16B for output, and its KV Cache HBM footprint is reduced to 1/4 that of the previous-generation V4. On HLE it scores 34.52%, below Astra's 50.40%, and Fireworks
Matched fieldsTitle
DeepSeek V4 Pro leads in code evaluation
On August 26, 2026, Fireworks AI released evaluation results for DeepSeek V4 Pro 0813 and announced that training support for the model is now live on Fireworks, supporting SFT, DPO, and RFT. The evaluation used four benchmark suites: SWE-Bench Verified, LiveCodeBench v6, Aider Polyglot, and Terminal-Bench 2.1. Fireworks stated that DeepSeek V4 Pro scored 95.2% on SWE-Bench Verified, higher than Kimi K3's 92.6% and Fable 5's 85.4%; on LiveCodeBench v6 it scored 92.0%. In terms of cost, the model spent $0.309 per task solved on SWE-Bench, compared with $0.808 for Fable 5; on LiveCodeBench the figures were $0.040 and $0.225, respectively. On a combined sample of 409 tasks, the oracle routing accuracy of DeepSeek V4 Pro and Fable 5 was 92.4%, higher than the 86.6% achieved by Fable 5 alone, with a per-task cost
On August 26, 2026, Fireworks AI released evaluation results for DeepSeek V4 Pro 0813 and announced that training support for the model is now live on Fireworks, supporting SFT, DPO, and RFT. The evaluation used four benchmark suites: SWE-Bench Verified, LiveCodeBench v6, Aider Polyglot, and Terminal-Bench 2.1. Fireworks stated that DeepSeek V4 Pro scored 95.2% on SWE-Bench Verified, higher than Kimi K3's 92.6% and Fable 5's 85.4%; on LiveCodeBench v6 it scored 92.0%. In terms of cost, the model
Matched fieldsTitle
Fireworks evaluates DeepSeek's new model
On September 14, 2026, Fireworks AI released and evaluated DeepSeek-V4.1-Flash. According to its published results, the model achieves 74.34% pass@1 on DeepSWE, on par with GPT-6-Astra's 74.12%; its cost per task is $0.43, about 1/15 that of Astra. The model is a 552B-parameter MoE, using separate activation budgets of 8B for input and 16B for output, and its KV Cache HBM footprint is reduced to 1/4 that of the previous-generation V4. On HLE it scores 34.52%, below Astra's 50.40%, and Fireworks considers it better suited to agentic coding than to highly difficult reasoning. On September 28, Fireworks AI released its first cache-aware router, FireRouter with Opus, which is now live in the CLI and offered for the first time as a standalone routing model; it can select among Claude Opus 5.5, GLM 5.3 and GLM 5.3 Flash based on task fit, prompt cache cost and switching cost; its internal A/B testing over more than a month showed coding task cost per session dropping from $15.36 to $6.63, a 57% reduction (±19 percentage points), with accuracy at pure O
Matched fieldsTitle
DeepSeek V4 Pro leads in code evaluation
On August 26, 2026, Fireworks AI released evaluation results for DeepSeek V4 Pro 0813 and announced that training support for the model is now live on Fireworks, supporting SFT, DPO, and RFT. The evaluation used four benchmark suites: SWE-Bench Verified, LiveCodeBench v6, Aider Polyglot, and Terminal-Bench 2.1. Fireworks stated that DeepSeek V4 Pro scored 95.2% on SWE-Bench Verified, higher than Kimi K3's 92.6% and Fable 5's 85.4%; on LiveCodeBench v6 it scored 92.0%. In terms of cost, the model spent $0.309 per task solved on SWE-Bench, compared with $0.808 for Fable 5; on LiveCodeBench the figures were $0.040 and $0.225, respectively. On a combined sample of 409 tasks, the oracle routing accuracy of DeepSeek V4 Pro and Fable 5 was 92.4%, higher than the 86.6% achieved by Fable 5 alone, with a per-task cost
Matched fieldsTitle