GPT-5 (Aug 2025)
openai/gpt-5-2025-08-07
GPT-5 is a model from OpenAI that accepts text, image, and file inputs and generates text outputs. It supports a context length of 400,000 tokens, tool use, and reasoning capabilities. It is a proprietary model released in January 2025.
- tool use
- structured outputs
- reasoning
At a glance
Specifications
What the API gives you
- Context window
- 400K tokens
- Max output
- 128K tokens
- Input price
- $1.25 / 1M tokens
- Output price
- $10 / 1M tokens
- Cache read
- $0.13 / 1M tokens
- Modalities
- text, image, file → text
- Knowledge cutoff
- Sep 30, 2024
- Released
- Jan 1, 2025
Measured evidence
Public benchmark record
- Aider Polyglot
- 88%2026-07-17
- Aider Polyglot
- 88%2026-07-21
- Aider Polyglot
- 88%2026-07-23
- Aider Polyglot
- 88%2026-07-27
- Aider Polyglot
- 88%2026-07-28
- Aider Polyglot
- 88%2026-07-29
- Aider Polyglot
- 88%2026-07-30
- Aider Polyglot
- 88%2026-07-31
- Aider Polyglot
- 88%2026-08-01
- Aider Polyglot
- 88%2026-08-02
- Aider Polyglot
- 88%2026-08-05
- Aider Polyglot
- 88%2026-08-03
- Aider Polyglot
- 88%2026-08-09
- Aider Polyglot
- 88%2026-08-04
- Aider Polyglot
- 88%2026-08-06
- Aider Polyglot
- 88%2026-08-07
- Aider Polyglot
- 88%2026-08-14
- Aider Polyglot
- 88%2026-08-08
- Aider Polyglot
- 88%2026-08-21
- Aider Polyglot
- 88%2026-08-10
- Aider Polyglot
- 88%2026-08-11
- Aider Polyglot
- 88%2026-08-18
- Aider Polyglot
- 88%2026-08-12
- Aider Polyglot
- 88%2026-08-19
- Aider Polyglot
- 88%2026-08-13
- Aider Polyglot
- 88%2026-08-15
- Aider Polyglot
- 88%2026-08-26
- Aider Polyglot
- 88%2026-08-20
- Aider Polyglot
- 88%2026-08-16
- Aider Polyglot
- 88%2026-08-17
- Aider Polyglot
- 88%2026-08-27
- Aider Polyglot
- 88%2026-08-22
- Aider Polyglot
- 88%2026-08-23
- Aider Polyglot
- 88%2026-08-24
- Aider Polyglot
- 88%2026-08-25
- Aider Polyglot
- 88%2026-09-05
- Aider Polyglot
- 88%2026-08-28
- Aider Polyglot
- 88%2026-09-06
- Aider Polyglot
- 88%2026-08-29
- Aider Polyglot
- 88%2026-08-30
- Aider Polyglot
- 88%2026-08-31
- Aider Polyglot
- 88%2026-09-01
- Aider Polyglot
- 88%2026-09-02
- Aider Polyglot
- 88%2026-09-03
- Aider Polyglot
- 88%2026-09-04
- Design Arena Coding
- 1196 Elo2026-07-28
- Design Arena Coding
- 1196 Elo2026-07-27
- Design Arena Coding
- 1196 Elo2026-07-30
- Design Arena Coding
- 1196 Elo2026-07-29
- Design Arena Coding
- 1195 Elo2026-07-31
- Design Arena Coding
- 1195 Elo2026-08-02
- Design Arena Coding
- 1194 Elo2026-08-05
- Design Arena Coding
- 1195 Elo2026-08-01
- Design Arena Coding
- 1193 Elo2026-08-09
- Design Arena Coding
- 1195 Elo2026-08-03
- Design Arena Coding
- 1194 Elo2026-08-04
- Design Arena Coding
- 1190 Elo2026-08-14
- Design Arena Coding
- 1194 Elo2026-08-06
- Design Arena Coding
- 1193 Elo2026-08-10
- Design Arena Coding
- 1194 Elo2026-08-07
- Design Arena Coding
- 1184 Elo2026-08-18
- Design Arena Coding
- 1193 Elo2026-08-08
- Design Arena Coding
- 1184 Elo2026-08-15
- Design Arena Coding
- 1193 Elo2026-08-11
- Design Arena Coding
- 1192 Elo2026-08-12
- Design Arena Coding
- 1190 Elo2026-08-13
- Design Arena Coding
- 1183 Elo2026-08-19
- Design Arena Coding
- 1189 Elo2026-08-27
- Design Arena Coding
- 1183 Elo2026-08-20
- Design Arena Coding
- 1184 Elo2026-08-16
- Design Arena Coding
- 1181 Elo2026-09-05
- Design Arena Coding
- 1184 Elo2026-08-17
- Design Arena Coding
- 1190 Elo2026-08-21
- Design Arena Coding
- 1190 Elo2026-08-22
- Design Arena Coding
- 1190 Elo2026-08-23
- Design Arena Coding
- 1189 Elo2026-08-28
- Design Arena Coding
- 1190 Elo2026-08-24
- Design Arena Coding
- 1190 Elo2026-08-25
- Design Arena Coding
- 1190 Elo2026-08-26
- Design Arena Coding
- 1181 Elo2026-09-06
- Design Arena Coding
- 1189 Elo2026-08-29
- Design Arena Coding
- 1189 Elo2026-08-30
- Design Arena Coding
- 1189 Elo2026-08-31
- Design Arena Coding
- 1189 Elo2026-09-01
- Design Arena Coding
- 1188 Elo2026-09-02
- Design Arena Coding
- 1185 Elo2026-09-03
- Design Arena Coding
- 1184 Elo2026-09-04
- Design Arena UI
- 1181 Elo2026-07-28
- Design Arena UI
- 1181 Elo2026-07-27
- Design Arena UI
- 1181 Elo2026-07-30
- Design Arena UI
- 1181 Elo2026-07-29
- Design Arena UI
- 1181 Elo2026-07-31
- Design Arena UI
- 1181 Elo2026-08-02
- Design Arena UI
- 1181 Elo2026-08-01
- Design Arena UI
- 1181 Elo2026-08-05
- Design Arena UI
- 1178 Elo2026-08-09
- Design Arena UI
- 1181 Elo2026-08-03
- Design Arena UI
- 1181 Elo2026-08-04
- Design Arena UI
- 1176 Elo2026-08-14
- Design Arena UI
- 1180 Elo2026-08-06
- Design Arena UI
- 1180 Elo2026-08-07
- Design Arena UI
- 1178 Elo2026-08-10
- Design Arena UI
- 1178 Elo2026-08-08
- Design Arena UI
- 1173 Elo2026-08-18
- Design Arena UI
- 1178 Elo2026-08-11
- Design Arena UI
- 1174 Elo2026-08-15
- Design Arena UI
- 1179 Elo2026-08-12
- Design Arena UI
- 1179 Elo2026-08-13
- Design Arena UI
- 1173 Elo2026-08-19
- Design Arena UI
- 1173 Elo2026-08-16
- Design Arena UI
- 1173 Elo2026-08-20
- Design Arena UI
- 1171 Elo2026-08-27
- Design Arena UI
- 1173 Elo2026-08-17
- Design Arena UI
- 1167 Elo2026-09-05
- Design Arena UI
- 1171 Elo2026-08-21
- Design Arena UI
- 1172 Elo2026-08-22
- Design Arena UI
- 1172 Elo2026-08-23
- Design Arena UI
- 1172 Elo2026-08-24
- Design Arena UI
- 1171 Elo2026-08-28
- Design Arena UI
- 1172 Elo2026-08-25
- Design Arena UI
- 1172 Elo2026-08-26
- Design Arena UI
- 1168 Elo2026-09-06
- Design Arena UI
- 1171 Elo2026-08-29
- Design Arena UI
- 1171 Elo2026-08-30
- Design Arena UI
- 1171 Elo2026-08-31
- Design Arena UI
- 1171 Elo2026-09-01
- Design Arena UI
- 1170 Elo2026-09-02
- Design Arena UI
- 1168 Elo2026-09-03
- Design Arena UI
- 1167 Elo2026-09-04
- Design Arena Website
- 1207 Elo2026-07-28
- Design Arena Website
- 1207 Elo2026-07-30
- Design Arena Website
- 1207 Elo2026-07-27
- Design Arena Website
- 1207 Elo2026-07-29
- Design Arena Website
- 1206 Elo2026-07-31
- Design Arena Website
- 1206 Elo2026-08-02
- Design Arena Website
- 1206 Elo2026-08-01
- Design Arena Website
- 1205 Elo2026-08-05
- Design Arena Website
- 1206 Elo2026-08-03
- Design Arena Website
- 1204 Elo2026-08-09
- Design Arena Website
- 1206 Elo2026-08-04
- Design Arena Website
- 1202 Elo2026-08-14
- Design Arena Website
- 1205 Elo2026-08-06
- Design Arena Website
- 1205 Elo2026-08-07
- Design Arena Website
- 1204 Elo2026-08-10
- Design Arena Website
- 1204 Elo2026-08-08
- Design Arena Website
- 1193 Elo2026-08-18
- Design Arena Website
- 1204 Elo2026-08-11
- Design Arena Website
- 1193 Elo2026-08-15
- Design Arena Website
- 1204 Elo2026-08-12
- Design Arena Website
- 1202 Elo2026-08-13
- Design Arena Website
- 1193 Elo2026-08-19
- Design Arena Website
- 1193 Elo2026-08-16
- Design Arena Website
- 1193 Elo2026-08-20
- Design Arena Website
- 1202 Elo2026-08-27
- Design Arena Website
- 1193 Elo2026-08-17
- Design Arena Website
- 1198 Elo2026-09-05
- Design Arena Website
- 1202 Elo2026-08-21
- Design Arena Website
- 1202 Elo2026-08-22
- Design Arena Website
- 1202 Elo2026-08-23
- Design Arena Website
- 1202 Elo2026-08-24
- Design Arena Website
- 1202 Elo2026-08-28
- Design Arena Website
- 1202 Elo2026-08-25
- Design Arena Website
- 1202 Elo2026-08-26
- Design Arena Website
- 1195 Elo2026-09-06
- Design Arena Website
- 1202 Elo2026-08-29
- Design Arena Website
- 1201 Elo2026-08-30
- Design Arena Website
- 1201 Elo2026-08-31
- Design Arena Website
- 1202 Elo2026-09-01
- Design Arena Website
- 1200 Elo2026-09-02
- Design Arena Website
- 1199 Elo2026-09-03
- Design Arena Website
- 1198 Elo2026-09-04
- LMArena Creative Writing
- 1365 Elo2026-07-21
- LMArena Creative Writing
- 1368 Elo2026-07-27
- LMArena Creative Writing
- 1368 Elo2026-07-30
- LMArena Creative Writing
- 1368 Elo2026-08-02
- LMArena Creative Writing
- 1368 Elo2026-08-03
- LMArena Creative Writing
- 1368 Elo2026-08-06
- LMArena Creative Writing
- 1367 Elo2026-08-12
- LMArena Creative Writing
- 1367 Elo2026-08-21
- LMArena Creative Writing
- 1366 Elo2026-09-02
- LMArena Creative Writing
- 1366 Elo2026-08-27
- LMArena Creative Writing
- 1366 Elo2026-09-01
- LMArena Instruction Following
- 1388 Elo2026-07-21
- LMArena Instruction Following
- 1388 Elo2026-07-27
- LMArena Instruction Following
- 1388 Elo2026-07-30
- LMArena Instruction Following
- 1388 Elo2026-08-02
- LMArena Instruction Following
- 1388 Elo2026-08-03
- LMArena Instruction Following
- 1388 Elo2026-08-06
- LMArena Instruction Following
- 1388 Elo2026-08-12
- LMArena Instruction Following
- 1388 Elo2026-08-21
- LMArena Instruction Following
- 1388 Elo2026-09-02
- LMArena Instruction Following
- 1388 Elo2026-08-27
- LMArena Instruction Following
- 1388 Elo2026-09-01
- LMArena Long Query
- 1387 Elo2026-07-21
- LMArena Long Query
- 1400 Elo2026-07-27
- LMArena Long Query
- 1400 Elo2026-07-30
- LMArena Long Query
- 1401 Elo2026-08-02
- LMArena Long Query
- 1401 Elo2026-08-06
- LMArena Long Query
- 1401 Elo2026-08-03
- LMArena Long Query
- 1399 Elo2026-08-12
- LMArena Long Query
- 1399 Elo2026-08-21
- LMArena Long Query
- 1399 Elo2026-09-02
- LMArena Long Query
- 1400 Elo2026-08-27
- LMArena Long Query
- 1399 Elo2026-09-01
- LMArena Math
- 1398 Elo2026-07-21
- LMArena Math
- 1409 Elo2026-07-27
- LMArena Math
- 1409 Elo2026-07-30
- LMArena Math
- 1409 Elo2026-08-02
- LMArena Math
- 1409 Elo2026-08-03
- LMArena Math
- 1409 Elo2026-08-06
- LMArena Math
- 1409 Elo2026-08-12
- LMArena Math
- 1409 Elo2026-08-21
- LMArena Math
- 1408 Elo2026-09-01
- LMArena Math
- 1408 Elo2026-08-27
- LMArena Text
- 1434 Elo2026-07-21
- LMArena Text
- 1434 Elo2026-07-27
- LMArena Text
- 1434 Elo2026-08-02
- LMArena Text
- 1434 Elo2026-07-30
- LMArena Text
- 1434 Elo2026-08-10
- LMArena Text
- 1434 Elo2026-08-06
- LMArena Text
- 1434 Elo2026-08-03
- LMArena Text
- 1434 Elo2026-08-21
- LMArena Text
- 1434 Elo2026-08-12
- LMArena Text
- 1434 Elo2026-08-27
- LMArena Text
- 1434 Elo2026-09-01
- LMArena Text
- 1434 Elo2026-09-02
- LMArena Vision
- 1225 Elo2026-07-26
- LMArena Vision
- 1225 Elo2026-07-30
- LMArena Vision
- 1225 Elo2026-08-02
- LMArena Vision
- 1225 Elo2026-08-06
- LMArena Vision
- 1226 Elo2026-08-21
- LMArena Vision
- 1225 Elo2026-08-27
- LMArena WebDev
- 1395 Elo2026-07-21
- LMArena WebDev
- 1419 Elo2026-07-27
- LMArena WebDev
- 1419 Elo2026-07-24
- LMArena WebDev
- 1419 Elo2026-07-28
- LMArena WebDev
- 1419 Elo2026-07-30
- LMArena WebDev
- 1419 Elo2026-08-01
- LMArena WebDev
- 1419 Elo2026-07-31
- LMArena WebDev
- 1419 Elo2026-08-06
- LMArena WebDev
- 1419 Elo2026-08-02
- LMArena WebDev
- 1419 Elo2026-08-12
- LMArena WebDev
- 1419 Elo2026-08-10
- LMArena WebDev
- 1419 Elo2026-08-14
- LMArena WebDev
- 1419 Elo2026-09-01
- LMArena WebDev
- 1419 Elo2026-09-05
- LMArena WebDev
- 1419 Elo2026-08-21
- LMArena WebDev
- 1419 Elo2026-08-30
- SWE-bench Verified
- 76.8%2025-09-02
- SWE-bench Verified
- 71.8%2025-08-07
- SWE-rebench‡
- 44.0% ± 0.82025-12-01tools
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.
Task evidence
How broad is the support?
Each status is exact to this model version and the selected task. Official release claims remain provisional.
- Best LLM for Frontend & UIEstablished evidence
90% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Debugging & Code ReviewEstablished evidence
85% of intended weighted task evidence across 4 independent sources. 6 of 6 configured evaluation feeds currently have results.
- Best Local LLM for CodingEstablished evidence
76% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for CodingEstablished evidence
74% of intended weighted task evidence across 5 independent sources. 8 of 8 configured evaluation feeds currently have results.
- Best LLM for Code CompletionEstablished evidence
63% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Business WritingProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Marketing CopyProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Chat & RoleplayProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Roleplay & CharacterProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Creative WritingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for WritingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Image UnderstandingProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Reasoning or VLMEvalKit tasks. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for a General AssistantProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Logic & Problem SolvingProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Competition MathProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Math & ReasoningProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best Value LLMProvisional evidence
36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best Open-Weight LLM for Self-HostingProvisional evidence
33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Autonomous AgentsProvisional evidence
29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for Fast SummariesProvisional evidence
29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Literary TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Best Cheap LLM for High VolumeProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Everyday TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Cheapest Capable LLMProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Massive ContextProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for OCR & DocumentsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Vision & DocumentsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Charts & DiagramsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Document ParsingProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Agentic CodingProvisional evidence
23% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.
- Best LLM for Document SummarizationProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for SummarizationProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for AI AgentsProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for Hermes AgentProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenHandsProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for GooseProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for RAG & Long ContextProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for OpenClawProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for JSON & Schema OutputProvisional evidence
17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Structured Data ExtractionProvisional evidence
17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for High-Volume ExtractionProvisional evidence
13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.
- Best LLM for Tool & Function CallingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Computer & Browser UseProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.
Recommendation coverage
Where this model appears
Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.