GPT-4.1 Mini
openai/gpt-4.1-mini-2025-04-14
OpenAI's GPT-4.1 Mini is a multimodal model that accepts image, text, and file inputs and generates text output. It has a context length of 1,047,576 tokens, supports tool use, does not support reasoning, and is not released with open weights. The model is priced at $0.40 per million input tokens and $1.60 per million output tokens, and it was released on 2025‑04‑14.
- tool use
- structured outputs
At a glance
Specifications
What the API gives you
- Context window
- 1.0M tokens
- Max output
- 33K tokens
- Input price
- $0.40 / 1M tokens
- Output price
- $1.60 / 1M tokens
- Cache read
- $0.100 / 1M tokens
- Modalities
- image, text, file → text
- Knowledge cutoff
- Jun 30, 2024
- Released
- Apr 14, 2025
Measured evidence
Public benchmark record
- Aider Polyglot
- 32.4%2026-07-17
- Aider Polyglot
- 32.4%2026-07-21
- Aider Polyglot
- 32.4%2026-07-23
- Aider Polyglot
- 32.4%2026-07-27
- Aider Polyglot
- 32.4%2026-07-28
- Aider Polyglot
- 32.4%2026-07-29
- Aider Polyglot
- 32.4%2026-07-30
- Aider Polyglot
- 32.4%2026-07-31
- Aider Polyglot
- 32.4%2026-08-01
- Aider Polyglot
- 32.4%2026-08-02
- Aider Polyglot
- 32.4%2026-08-05
- Aider Polyglot
- 32.4%2026-08-03
- Aider Polyglot
- 32.4%2026-08-09
- Aider Polyglot
- 32.4%2026-08-04
- Aider Polyglot
- 32.4%2026-08-06
- Aider Polyglot
- 32.4%2026-08-07
- Aider Polyglot
- 32.4%2026-08-14
- Aider Polyglot
- 32.4%2026-08-08
- Aider Polyglot
- 32.4%2026-08-10
- Aider Polyglot
- 32.4%2026-08-15
- Aider Polyglot
- 32.4%2026-08-11
- Aider Polyglot
- 32.4%2026-08-18
- Aider Polyglot
- 32.4%2026-08-12
- Aider Polyglot
- 32.4%2026-08-19
- Aider Polyglot
- 32.4%2026-08-13
- Aider Polyglot
- 32.4%2026-08-20
- Aider Polyglot
- 32.4%2026-08-16
- Aider Polyglot
- 32.4%2026-08-17
- Aider Polyglot
- 32.4%2026-08-21
- Aider Polyglot
- 32.4%2026-08-27
- Aider Polyglot
- 32.4%2026-08-22
- Aider Polyglot
- 32.4%2026-08-23
- Aider Polyglot
- 32.4%2026-08-24
- Aider Polyglot
- 32.4%2026-08-25
- Aider Polyglot
- 32.4%2026-09-05
- Aider Polyglot
- 32.4%2026-08-26
- Aider Polyglot
- 32.4%2026-08-28
- Aider Polyglot
- 32.4%2026-09-06
- Aider Polyglot
- 32.4%2026-08-29
- Aider Polyglot
- 32.4%2026-08-30
- Aider Polyglot
- 32.4%2026-08-31
- Aider Polyglot
- 32.4%2026-09-01
- Aider Polyglot
- 32.4%2026-09-02
- Aider Polyglot
- 32.4%2026-09-03
- Aider Polyglot
- 32.4%2026-09-04
- BFCL
- 50.5%2026-07-28
- BFCL
- 50.5%2026-07-27
- BFCL
- 50.5%2026-07-29
- BFCL
- 50.5%2026-07-31
- BFCL
- 50.5%2026-07-30
- BFCL
- 50.5%2026-08-02
- BFCL
- 50.5%2026-08-01
- BFCL
- 50.5%2026-08-05
- BFCL
- 50.5%2026-08-03
- BFCL
- 50.5%2026-08-09
- BFCL
- 50.5%2026-08-04
- BFCL
- 50.5%2026-08-06
- BFCL
- 50.5%2026-08-07
- BFCL
- 50.5%2026-08-14
- BFCL
- 50.5%2026-08-10
- BFCL
- 50.5%2026-08-08
- BFCL
- 50.5%2026-08-11
- BFCL
- 50.5%2026-08-18
- BFCL
- 50.5%2026-08-15
- BFCL
- 50.5%2026-08-12
- BFCL
- 50.5%2026-08-13
- BFCL
- 50.5%2026-08-19
- BFCL
- 50.5%2026-08-16
- BFCL
- 50.5%2026-08-20
- BFCL
- 50.5%2026-08-27
- BFCL
- 50.5%2026-08-17
- BFCL
- 50.5%2026-08-21
- BFCL
- 50.5%2026-08-22
- BFCL
- 50.5%2026-08-23
- BFCL
- 50.5%2026-08-24
- BFCL
- 50.5%2026-09-05
- BFCL
- 50.5%2026-08-28
- BFCL
- 50.5%2026-08-25
- BFCL
- 50.5%2026-08-26
- BFCL
- 50.5%2026-09-06
- BFCL
- 50.5%2026-08-29
- BFCL
- 50.5%2026-08-30
- BFCL
- 50.5%2026-08-31
- BFCL
- 50.5%2026-09-01
- BFCL
- 50.5%2026-09-02
- BFCL
- 50.5%2026-09-03
- BFCL
- 50.5%2026-09-04
- Design Arena Coding
- 1024 Elo2026-07-28
- Design Arena Coding
- 1024 Elo2026-07-27
- Design Arena Coding
- 1024 Elo2026-07-30
- Design Arena Coding
- 1024 Elo2026-07-29
- Design Arena Coding
- 1024 Elo2026-07-31
- Design Arena Coding
- 1023 Elo2026-08-02
- Design Arena Coding
- 1022 Elo2026-08-05
- Design Arena Coding
- 1023 Elo2026-08-01
- Design Arena Coding
- 1021 Elo2026-08-09
- Design Arena Coding
- 1023 Elo2026-08-03
- Design Arena Coding
- 1023 Elo2026-08-04
- Design Arena Coding
- 1018 Elo2026-08-14
- Design Arena Coding
- 1022 Elo2026-08-06
- Design Arena Coding
- 1021 Elo2026-08-10
- Design Arena Coding
- 1023 Elo2026-08-07
- Design Arena Coding
- 1012 Elo2026-08-18
- Design Arena Coding
- 1022 Elo2026-08-08
- Design Arena Coding
- 1013 Elo2026-08-15
- Design Arena Coding
- 1021 Elo2026-08-11
- Design Arena Coding
- 1020 Elo2026-08-12
- Design Arena Coding
- 1019 Elo2026-08-13
- Design Arena Coding
- 1011 Elo2026-08-19
- Design Arena Coding
- 1018 Elo2026-08-27
- Design Arena Coding
- 1011 Elo2026-08-20
- Design Arena Coding
- 1012 Elo2026-08-16
- Design Arena Coding
- 1010 Elo2026-09-05
- Design Arena Coding
- 1012 Elo2026-08-17
- Design Arena Coding
- 1018 Elo2026-08-21
- Design Arena Coding
- 1018 Elo2026-08-22
- Design Arena Coding
- 1018 Elo2026-08-23
- Design Arena Coding
- 1018 Elo2026-08-28
- Design Arena Coding
- 1018 Elo2026-08-24
- Design Arena Coding
- 1018 Elo2026-08-25
- Design Arena Coding
- 1019 Elo2026-08-26
- Design Arena Coding
- 1010 Elo2026-09-06
- Design Arena Coding
- 1018 Elo2026-08-29
- Design Arena Coding
- 1017 Elo2026-08-30
- Design Arena Coding
- 1017 Elo2026-08-31
- Design Arena Coding
- 1017 Elo2026-09-01
- Design Arena Coding
- 1016 Elo2026-09-02
- Design Arena Coding
- 1014 Elo2026-09-03
- Design Arena Coding
- 1013 Elo2026-09-04
- Design Arena UI
- 998 Elo2026-07-28
- Design Arena UI
- 998 Elo2026-07-27
- Design Arena UI
- 998 Elo2026-07-30
- Design Arena UI
- 998 Elo2026-07-29
- Design Arena UI
- 998 Elo2026-07-31
- Design Arena UI
- 998 Elo2026-08-02
- Design Arena UI
- 998 Elo2026-08-01
- Design Arena UI
- 997 Elo2026-08-05
- Design Arena UI
- 998 Elo2026-08-03
- Design Arena UI
- 994 Elo2026-08-09
- Design Arena UI
- 997 Elo2026-08-04
- Design Arena UI
- 992 Elo2026-08-14
- Design Arena UI
- 997 Elo2026-08-06
- Design Arena UI
- 996 Elo2026-08-07
- Design Arena UI
- 994 Elo2026-08-10
- Design Arena UI
- 995 Elo2026-08-08
- Design Arena UI
- 989 Elo2026-08-18
- Design Arena UI
- 994 Elo2026-08-11
- Design Arena UI
- 990 Elo2026-08-15
- Design Arena UI
- 995 Elo2026-08-12
- Design Arena UI
- 995 Elo2026-08-13
- Design Arena UI
- 989 Elo2026-08-19
- Design Arena UI
- 989 Elo2026-08-16
- Design Arena UI
- 989 Elo2026-08-20
- Design Arena UI
- 987 Elo2026-08-27
- Design Arena UI
- 989 Elo2026-08-17
- Design Arena UI
- 983 Elo2026-09-05
- Design Arena UI
- 988 Elo2026-08-21
- Design Arena UI
- 988 Elo2026-08-22
- Design Arena UI
- 988 Elo2026-08-23
- Design Arena UI
- 988 Elo2026-08-24
- Design Arena UI
- 987 Elo2026-08-28
- Design Arena UI
- 988 Elo2026-08-25
- Design Arena UI
- 988 Elo2026-08-26
- Design Arena UI
- 984 Elo2026-09-06
- Design Arena UI
- 987 Elo2026-08-29
- Design Arena UI
- 988 Elo2026-08-30
- Design Arena UI
- 987 Elo2026-08-31
- Design Arena UI
- 987 Elo2026-09-01
- Design Arena UI
- 987 Elo2026-09-02
- Design Arena UI
- 985 Elo2026-09-03
- Design Arena UI
- 983 Elo2026-09-04
- Design Arena Website
- 1022 Elo2026-07-28
- Design Arena Website
- 1022 Elo2026-07-30
- Design Arena Website
- 1022 Elo2026-07-27
- Design Arena Website
- 1022 Elo2026-07-29
- Design Arena Website
- 1022 Elo2026-07-31
- Design Arena Website
- 1021 Elo2026-08-02
- Design Arena Website
- 1021 Elo2026-08-01
- Design Arena Website
- 1021 Elo2026-08-05
- Design Arena Website
- 1021 Elo2026-08-03
- Design Arena Website
- 1020 Elo2026-08-09
- Design Arena Website
- 1021 Elo2026-08-04
- Design Arena Website
- 1017 Elo2026-08-14
- Design Arena Website
- 1021 Elo2026-08-06
- Design Arena Website
- 1021 Elo2026-08-07
- Design Arena Website
- 1020 Elo2026-08-10
- Design Arena Website
- 1020 Elo2026-08-08
- Design Arena Website
- 1009 Elo2026-08-18
- Design Arena Website
- 1020 Elo2026-08-11
- Design Arena Website
- 1008 Elo2026-08-15
- Design Arena Website
- 1019 Elo2026-08-12
- Design Arena Website
- 1017 Elo2026-08-13
- Design Arena Website
- 1009 Elo2026-08-19
- Design Arena Website
- 1008 Elo2026-08-16
- Design Arena Website
- 1009 Elo2026-08-20
- Design Arena Website
- 1017 Elo2026-08-27
- Design Arena Website
- 1008 Elo2026-08-17
- Design Arena Website
- 1013 Elo2026-09-05
- Design Arena Website
- 1017 Elo2026-08-21
- Design Arena Website
- 1017 Elo2026-08-22
- Design Arena Website
- 1017 Elo2026-08-23
- Design Arena Website
- 1017 Elo2026-08-24
- Design Arena Website
- 1017 Elo2026-08-28
- Design Arena Website
- 1018 Elo2026-08-25
- Design Arena Website
- 1018 Elo2026-08-26
- Design Arena Website
- 1011 Elo2026-09-06
- Design Arena Website
- 1017 Elo2026-08-29
- Design Arena Website
- 1016 Elo2026-08-30
- Design Arena Website
- 1017 Elo2026-08-31
- Design Arena Website
- 1017 Elo2026-09-01
- Design Arena Website
- 1015 Elo2026-09-02
- Design Arena Website
- 1014 Elo2026-09-03
- Design Arena Website
- 1013 Elo2026-09-04
- LMArena Creative Writing
- 1301 Elo2026-07-21
- LMArena Creative Writing
- 1301 Elo2026-07-27
- LMArena Creative Writing
- 1301 Elo2026-07-30
- LMArena Creative Writing
- 1301 Elo2026-08-02
- LMArena Creative Writing
- 1301 Elo2026-08-03
- LMArena Creative Writing
- 1301 Elo2026-08-06
- LMArena Creative Writing
- 1300 Elo2026-08-12
- LMArena Creative Writing
- 1300 Elo2026-08-21
- LMArena Creative Writing
- 1300 Elo2026-09-02
- LMArena Creative Writing
- 1300 Elo2026-08-27
- LMArena Creative Writing
- 1299 Elo2026-09-01
- LMArena Instruction Following
- 1332 Elo2026-07-21
- LMArena Instruction Following
- 1332 Elo2026-07-27
- LMArena Instruction Following
- 1332 Elo2026-07-30
- LMArena Instruction Following
- 1332 Elo2026-08-02
- LMArena Instruction Following
- 1332 Elo2026-08-03
- LMArena Instruction Following
- 1332 Elo2026-08-06
- LMArena Instruction Following
- 1332 Elo2026-08-12
- LMArena Instruction Following
- 1332 Elo2026-08-21
- LMArena Instruction Following
- 1332 Elo2026-09-02
- LMArena Instruction Following
- 1332 Elo2026-08-27
- LMArena Instruction Following
- 1332 Elo2026-09-01
- LMArena Long Query
- 1344 Elo2026-07-21
- LMArena Long Query
- 1344 Elo2026-07-27
- LMArena Long Query
- 1344 Elo2026-07-30
- LMArena Long Query
- 1344 Elo2026-08-02
- LMArena Long Query
- 1344 Elo2026-08-03
- LMArena Long Query
- 1344 Elo2026-08-06
- LMArena Long Query
- 1343 Elo2026-08-12
- LMArena Long Query
- 1343 Elo2026-08-21
- LMArena Long Query
- 1343 Elo2026-09-02
- LMArena Long Query
- 1343 Elo2026-08-27
- LMArena Long Query
- 1343 Elo2026-09-01
- LMArena Math
- 1343 Elo2026-07-21
- LMArena Math
- 1344 Elo2026-07-27
- LMArena Math
- 1344 Elo2026-07-30
- LMArena Math
- 1343 Elo2026-08-02
- LMArena Math
- 1343 Elo2026-08-03
- LMArena Math
- 1343 Elo2026-08-06
- LMArena Math
- 1343 Elo2026-08-12
- LMArena Math
- 1343 Elo2026-08-21
- LMArena Math
- 1343 Elo2026-09-01
- LMArena Math
- 1343 Elo2026-08-27
- LMArena Text
- 1383 Elo2026-07-21
- LMArena Text
- 1383 Elo2026-07-27
- LMArena Text
- 1383 Elo2026-07-30
- LMArena Text
- 1383 Elo2026-08-10
- LMArena Text
- 1383 Elo2026-08-02
- LMArena Text
- 1383 Elo2026-08-06
- LMArena Text
- 1383 Elo2026-08-03
- LMArena Text
- 1383 Elo2026-08-21
- LMArena Text
- 1383 Elo2026-08-12
- LMArena Text
- 1382 Elo2026-09-01
- LMArena Text
- 1382 Elo2026-09-02
- LMArena Text
- 1382 Elo2026-08-27
- LMArena Vision
- 1183 Elo2026-07-12
- LMArena Vision
- 1202 Elo2026-07-21
- LMArena Vision
- 1203 Elo2026-07-26
- LMArena Vision
- 1203 Elo2026-07-30
- LMArena Vision
- 1203 Elo2026-08-02
- LMArena Vision
- 1203 Elo2026-08-06
- LMArena Vision
- 1202 Elo2026-08-21
- LMArena Vision
- 1201 Elo2026-08-27
- SWE-rebench‡
- 25.5% ± 0.52025-08-01text
- SWE-rebench‡
- 15.8% ± 0.72025-12-01tools
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 Debugging & Code ReviewEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 6 of 6 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 Tool & Function CallingProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 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 Frontend & UIProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.
- Best Local LLM for CodingProvisional evidence
56% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Hermes AgentProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenHandsProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for GooseProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenClawProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 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 CodingProvisional evidence
50% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 8 of 8 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 AI AgentsProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 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 LLM for JSON & Schema OutputProvisional evidence
33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Structured Data ExtractionProvisional evidence
33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 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 Code CompletionProvisional evidence
31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 4 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 Computer & Browser UseProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 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 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 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.