Skip to content
geekradar
Latest
AI
Games
Movies & TV
Gear
Science
Compare
Search news
Search results
Int
International
Italy
Trending
Gaming
PC gaming
Smartphones
NASA
Apple
Consumer technology
Streaming
Television
Android
PlayStation
Google
Steam
Space
Privacy
Xbox
Open source
Microsoft
NVIDIA
Cybersecurity
Audio
Nintendo Switch 2
Semiconductors
Game updates
Indie games
Mobile gaming
Astronomy
Samsung
Netflix
Productivity
Mobile photography
Co-op gaming
Game design
All topics
Explore GeekRadar
Latest
AI
Games
Movies & TV
Gear
Science
Compare
More to explore
Good gear
All topics
About us
Say hello
GeekRadar / The comparison desk
COMPARE.
AI
AI
6,269
Devices
31,631
CPUs
40,283
GPUs
30,354
Cameras
1,501
Filters
Filter AI models
Search catalog
Rank by benchmark
All catalogue entries
$OneMillion-Bench (expert score) · version unreported · reported score · ?
$OneMillion-Bench (expert score) · version unreported · reported score · ?
$OneMillion-Bench (expert score) · version unreported · reported score · max · ?
Agentic coding DeepSWE 1.1 · 1.1 · reported score · Claude Code · ?
Agentic coding SWE-bench Pro · version unreported · reported score · Claude Code · Refined task set with corrected problematic tasks · ?
Agentic coding SWE-bench Pro · version unreported · reported score · Not specified · Not specified · max · Previously reported result; re-evaluation not stated · ?
Agentic terminal coding Terminal Bench 2.1 (Terminus) · 2.1 · reported score · Terminus · ?
Agentic terminal coding Terminal Bench 2.1 (Terminus) · 2.1 · reported score · Terminus · max · ?
Agents' Last Exam (Pass / Score) · version unreported · Pass · ?
Agents' Last Exam (Pass / Score) · version unreported · Pass · max · ?
Agents' Last Exam (Pass / Score) · version unreported · Score · ?
Agents' Last Exam (Pass / Score) · version unreported · Score · max · ?
AI2D_TEST · version unreported · reported score · ?
AIME26 · version unreported · reported score · Full AIME 2026 I and II · ?
AndroidBench · version unreported · reported score · Public subset · avg@3 · ?
AndroidBench · version unreported · reported score · Public subset · avg@3 · ?
AndroidBench · version unreported · reported score · Public subset · max · avg@3 · ?
Application recreation RecreationBench · version unreported · reported score · Internal · ?
Automation-Bench (Pass@1) · version unreported · reported score · Public subset · ?
Automation-Bench (Pass@1) · version unreported · reported score · Public subset · ?
Automation-Bench (Pass@1) · version unreported · reported score · Public subset · max · ?
Browser use WebArena-Verified · version unreported · reported score · OSWorld scaffold; official WebArena-Verified grader · ?
C-Eval · version unreported · reported score · ?
CC-OCR · version unreported · reported score · ?
CharXiv(RQ) · version unreported · reported score · ?
Claw-Eval Avg · version unreported · reported score · ?
Claw-Eval Pass^3 · version unreported · reported score · ?
Competitive coding LiveCodeBench v6 · 6 · reported score · ?
Competitive coding LiveCodeBench v6 · 6 · reported score · max · ?
Computer use OSWorld-Verified · version unreported · reported score · ?
Computer use OSWorld-Verified · version unreported · reported score · max · ?
CoWorkBench · version unreported · reported score · Internal · ?
CoWorkBench · version unreported · reported score · Internal · ?
CoWorkBench · version unreported · reported score · Internal · max · ?
DeepPlanning · version unreported · reported score · ?
DeepSWE 1.1 · 1.1 · reported score · Claude Code · Highest result across two harnesses · ?
DeepSWE 1.1 · 1.1 · reported score · Claude Code or mini-SWE-agent; winning harness unspecified · Highest result across two harnesses · ?
DeepSWE 1.1 · 1.1 · reported score · Claude Code or mini-SWE-agent; winning harness unspecified · Highest result across two harnesses · ?
DeepSWE 1.1 · 1.1 · reported score · Claude Code or mini-SWE-agent; winning harness unspecified · max · Highest result across two harnesses · ?
Document intelligence OmniDocBench 1.5 · 1.5 · reported score · ?
Document intelligence OmniDocBench 1.5 · 1.5 · reported score · max · ?
Embodied intelligence ERQA · version unreported · reported score · ?
Embodied intelligence ERQA · version unreported · reported score · max · ?
EmbSpatialBench · version unreported · reported score · ?
Frontier agentic tasks Agents' Last Exam · version unreported · pass@1 · ?
Frontier agentic tasks Agents' Last Exam · version unreported · score · ?
FrontierSWE · version unreported · reported score · Claude Code · Dominance recomputed from raw results · ?
FrontierSWE · version unreported · reported score · Not specified · Dominance recomputed from raw results · ?
FrontierSWE · version unreported · reported score · Not specified · Dominance recomputed from raw results · ?
General visual reasoning BabyVision · version unreported · reported score · Code interpreter disabled · ?
General visual reasoning BabyVision · version unreported · reported score · Code interpreter disabled · max · ?
General visual reasoning BabyVision · version unreported · reported score · Code interpreter enabled · ?
GPQA · version unreported · reported score · ?
GPQA Diamond · version unreported · reported score · ?
GPQA Diamond · version unreported · reported score · ?
GPQA Diamond · version unreported · reported score · max · ?
HallusionBench · version unreported · reported score · ?
HealthBench · version unreported · reported score · ?
HealthBench · version unreported · reported score · max · ?
HLE · version unreported · reported score · ?
HLE · version unreported · reported score · Disabled · ?
HLE · version unreported · reported score · Disabled · ?
HLE · version unreported · reported score · Disabled · max · ?
HLE w/ tools · version unreported · reported score · Enabled · ?
HLE w/ tools · version unreported · reported score · Enabled · ?
HLE w/ tools · version unreported · reported score · Enabled · max · ?
HMMT Feb 25 · version unreported · reported score · ?
HMMT Feb 26 · version unreported · reported score · ?
HMMT Nov 25 · version unreported · reported score · ?
IFBench · version unreported · reported score · ?
IFBench · version unreported · reported score · ?
IFBench · version unreported · reported score · max · ?
IMOAnswerBench · version unreported · reported score · ?
Instruction following IFBench · version unreported · reported score · ?
Instruction following IFBench · version unreported · reported score · max · ?
JobBench · version unreported · reported score · ?
JobBench · version unreported · reported score · ?
JobBench · version unreported · reported score · max · ?
LiveCodeBench v6 · 6 · reported score · ?
Long-horizon office work CoWorkBench · version unreported · reported score · Internal · ?
Long-horizon office work CoWorkBench · version unreported · reported score · Internal · max · ?
LongBench v2 · 2 · reported score · ?
LongBench v2 · 2 · reported score · max · ?
LVBench · version unreported · reported score · ?
Mathvista(mini) · version unreported · reported score · ?
MCP-Atlas · version unreported · reported score · Public set · ?
MCPMark · version unreported · reported score · GitHub MCP v0.30.3 · ?
MLS-Bench-Lite · version unreported · reported score · Claude Code · ?
MLS-Bench-Lite · version unreported · reported score · Not specified · ?
MLS-Bench-Lite · version unreported · reported score · Not specified · ?
MLS-Bench-Lite · version unreported · reported score · Not specified · max · ?
MLVU · version unreported · reported score · ?
MMBench EN-DEV-v1.1 · 1.1 · reported score · ?
MMLU-Pro · version unreported · reported score · ?
MMLU-Redux · version unreported · reported score · ?
MMMU · version unreported · reported score · ?
MMMU-Pro · version unreported · reported score · ?
MMMU-Pro · version unreported · reported score · ?
Mobile use AndroidWorld · version unreported · reported score · ?
Mobile use AndroidWorld · version unreported · reported score · max · ?
MRCR v2 256K (8-needle) · 2 · reported score · ?
MRCR v2 256K (8-needle) · 2 · reported score · max · ?
Multidisciplinary reasoning HLE · version unreported · reported score · ?
Multidisciplinary reasoning HLE · version unreported · reported score · max · ?
Multimodal software engineering SWE-MM · version unreported · reported score · Claude Code · Public SWE-bench Multimodal dev split with Opus 4.7 system-card appendix 8.3 modifications · ?
Multimodal software engineering SWE-MM · version unreported · reported score · Claude Code · Public SWE-bench Multimodal dev split with Opus 4.7 system-card appendix 8.3 modifications · max · ?
Multimodal tool use ClawEval-MM · version unreported · average score · max · Mean benchmark score over three trials · ?
Multimodal tool use ClawEval-MM · version unreported · average score · Mean benchmark score over three trials · ?
Multimodal tool use ClawEval-MM · version unreported · pass@3 · At least one success in three trials · ?
Multimodal tool use ClawEval-MM · version unreported · pass@3 · max · At least one success in three trials · ?
MVBench · version unreported · reported score · ?
NL2Repo · version unreported · reported score · Claude Code · ?
NL2Repo · version unreported · reported score · Not specified · ?
NL2Repo-Bench · version unreported · reported score · Claude Code · Repository acquisition commands disabled · ?
ODInW13 · version unreported · reported score · ?
OmniDocBench1.5 · 1.5 · reported score · ?
PaperBench · version unreported · reported score · BasicAgent · ?
PaperBench · version unreported · reported score · BasicAgent · ?
PaperBench · version unreported · reported score · BasicAgent · max · ?
PLawBench · version unreported · reported score · ?
PLawBench · version unreported · reported score · ?
PLawBench · version unreported · reported score · max · ?
PRBench-Finance · version unreported · reported score · ?
PRBench-Finance · version unreported · reported score · ?
PRBench-Finance · version unreported · reported score · max · ?
PRBench-Legal · version unreported · reported score · ?
PRBench-Legal · version unreported · reported score · ?
PRBench-Legal · version unreported · reported score · max · ?
Professional job tasks JobBench · version unreported · reported score · ?
QwenClawBench · version unreported · reported score · Internal real-user distribution · ?
QwenQoderBench · version unreported · reported score · Claude Code · Internal · avg@5 · ?
QwenQoderBench · version unreported · reported score · Claude Code · Internal · avg@5 · ?
QwenQoderBench · version unreported · reported score · Claude Code · Internal · max · avg@5 · ?
QwenReactBench · version unreported · reported score · Claude Code · Internal · ?
QwenReactBench · version unreported · reported score · Claude Code · Internal · ?
QwenReactBench · version unreported · reported score · Claude Code · Internal · max · ?
QwenSVGBench · version unreported · reported score · Not specified · Internal · ?
QwenSVGBench · version unreported · reported score · Not specified · Internal · ?
QwenSVGBench · version unreported · reported score · Not specified · Internal · max · ?
QwenSWEBench · version unreported · reported score · Claude Code · Internal · avg@3 · ?
QwenSWEBench · version unreported · reported score · Claude Code · Internal · avg@3 · ?
QwenSWEBench · version unreported · reported score · Claude Code · Internal · max · avg@3 · ?
QwenWebBench · version unreported · reported score · Internal · ?
Real-world perception RealWorldQA · version unreported · reported score · ?
Real-world perception RealWorldQA · version unreported · reported score · max · ?
RealWorldQA · version unreported · reported score · ?
RefCOCO(avg) · version unreported · reported score · ?
RefSpatialBench · version unreported · reported score · ?
Repo-level code generation NL2Repo-Bench · version unreported · reported score · Claude Code · Repository acquisition commands disabled · ?
Repo-level code generation NL2Repo-Bench · version unreported · reported score · Claude Code · Repository acquisition commands disabled · max · ?
Scientific chart analysis CharXiv (RQ) · version unreported · reported score · Code interpreter disabled · ?
Scientific chart analysis CharXiv (RQ) · version unreported · reported score · Code interpreter disabled · max · ?
Scientific chart analysis CharXiv (RQ) · version unreported · reported score · Code interpreter enabled · ?
Scientific chart analysis CharXiv (RQ) · version unreported · reported score · Not specified · ?
Scientific reasoning GPQA Diamond · version unreported · reported score · ?
Scientific reasoning GPQA Diamond · version unreported · reported score · max · ?
SimpleVQA · version unreported · reported score · ?
SkillsBench · version unreported · reported score · Claude Code · Public SkillsBench v1.1 · Average of three runs per task · ?
SkillsBench · version unreported · reported score · Claude Code · Public SkillsBench v1.1 · Average of three runs per task · ?
SkillsBench · version unreported · reported score · Codex · Public SkillsBench v1.1 · max · Average of three runs per task · ?
SkillsBench · version unreported · reported score · OpenCode · Public SkillsBench v1.1 · Average of three runs per task · ?
SkillsBench Avg5 · version unreported · reported score · OpenCode · Self-contained subset, API-dependent tasks excluded · Mean of five runs · ?
Software engineering QwenSWEBench · version unreported · reported score · Claude Code · Internal · avg@3 · ?
Software engineering QwenSWEBench · version unreported · reported score · Claude Code · Internal · max · avg@3 · ?
Source-reported benchmark · version unreported · intelligence · ?
SuperGPQA · version unreported · reported score · ?
SWE-bench Multilingual · version unreported · reported score · Internal agent scaffold: bash and file editing · Public benchmark · ?
SWE-bench Pro · version unreported · reported score · Claude Code · Refined task set with corrected problematic tasks · ?
SWE-bench Pro · version unreported · reported score · Claude Code · Refined task set with corrected problematic tasks · ?
SWE-bench Pro · version unreported · reported score · Claude Code · Refined task set with corrected problematic tasks · max · ?
SWE-bench Pro · version unreported · reported score · Internal agent scaffold: bash and file editing · Corrected public SWE-bench Pro task set · ?
SWE-bench Verified · version unreported · reported score · Internal agent scaffold: bash and file editing · Public benchmark · ?
TAU3-Bench · version unreported · reported score · ?
Terminal Bench 2.1 · 2.1 · reported score · Claude Code · avg@10 · ?
Terminal Bench 2.1 · 2.1 · reported score · Codex · max · Best published result across harnesses · ?
Terminal Bench 2.1 · 2.1 · reported score · Harness not specified · Best published result across harnesses · ?
Terminal Bench 2.1 · 2.1 · reported score · Terminus 2 · Best published result across harnesses · ?
Terminal Bench 2.1 · 2.1 · reported score · Terminus 2 · Best published result across harnesses · ?
Terminal-Bench 2.0 · 2.0 · reported score · Harbor/Terminus-2 · Mean of five runs · ?
Tool Decathlon · version unreported · reported score · ?
Toolathlon Verified (Pass@1) · version unreported · reported score · ?
Toolathlon Verified (Pass@1) · version unreported · reported score · ?
Toolathlon Verified (Pass@1) · version unreported · reported score · max · ?
VideoMME (w sub.) · version unreported · reported score · ?
VideoMME (w/o sub.) · version unreported · reported score · ?
VideoMMMU · version unreported · reported score · ?
Visual math problem solving MathVision · version unreported · reported score · Code interpreter disabled · ?
Visual math problem solving MathVision · version unreported · reported score · Code interpreter disabled · ?
Visual math problem solving MathVision · version unreported · reported score · Code interpreter disabled · max · ?
Visual math problem solving MathVision · version unreported · reported score · Code interpreter enabled · ?
Visual web development Vision2Web · version unreported · reported score · Claude Code · Category average · ?
VITA-Bench · version unreported · reported score · Average subdomain score · ?
WideSearch · version unreported · reported score · ?
WideSearch · version unreported · reported score · Claude Code · Average item F1 over four runs · ?
WideSearch · version unreported · reported score · Claude Code · Average item F1 over four runs · ?
WideSearch · version unreported · reported score · Qwen-Agent · Average item F1 over four runs · ?
WorkSpaceBench · version unreported · reported score · ?
WorkSpaceBench · version unreported · reported score · ?
WorkSpaceBench · version unreported · reported score · max · ?
ZEROBench_sub · version unreported · reported score · ?
Brand
All brands
01-ai
01.ai
abacusai
ai21
aion-labs
aisingapore
aleph-alpha
alibaba
allenai
amazon
ant-group
anthracite-org
anthropic
apodex
arcee-ai
baai
baichuan
baidu
black-forest-labs
bytedance
bytedance-seed
canopylabs
cerebras systems
cloudflare
cognitivecomputations
cohere
cohere,cohere labs (formerly cohere for ai)
databricks
deepreinforce
deepseek
deepseek,peking university
essentialai
fireworks
google
google deepmind,google
gryphe
hugging face,servicenow,nvidia,bigcode
huggingface
ibm
inception
inception-ai
inclusionai
inference-net
internlm
levanto
lightonai
liquid
mancer
meituan
meta
microsoft
microsoft research
mindlab
minimax
mistral
mixedbread
moonshot
moonshotai
morph
mosaicml
motif-technologies
nace-ai
nex-agi
Not reported
nousresearch
nvidia
openai
openbmb
paddlepaddle
perceptron
perplexity
phocinae
poolside
prime intellect,hugging face,arcee ai
quiverai
recursive
reflection
rekaai
relace
sakana
salesforce
sao10k
sarvam
sdaia
stability ai
stepfun
swiss-ai
tencent
thedrummer
thinking machines
thinkingmachines
thinky
tii
trendyol
typesafe
unbiased
undi95
Unspecified
upstage
vispark
vivgrid
writer
xai
xiaomi
zai
zhipuai
Benchmark coverage
With benchmark results
Apply filters
Clear all filters
Type
All types
Models
Arena evaluations
6,269 results
Sort by
Newest releases
Name A–Z
Most specifications
Not reported
yi-34b-chat
Arena evaluations
Model license
Yi License
Not reported
yi-lightning
Arena evaluations
Model license
Proprietary
Not reported
zephyr-7b-alpha
Arena evaluations
Model license
MIT
Not reported
zephyr-7b-beta
Arena evaluations
Model license
MIT
Not reported
zephyr-orpo-141b-A35b-v0.1
Arena evaluations
Model license
Apache 2.0
1
…
261
262
Explore comparisons
Claude Sonnet 4.5 vs GPT-5
Gemini 2.5 Flash vs Gemini 2.5 Pro
GPT-5 Mini vs GPT-5 Nano
Claude Opus 4 vs Claude Sonnet 4
0
selected
Compare
0
Open a record to read its complete specifications. Interactive selection requires JavaScript.