An interactive radar · 75 models · 52 benchmarks · 1084 sourced scores

The Race for the Frontier

Every major AI model against the benchmarks that defined the field, drawn as a radar (the same data is also on the line-chart view). Every benchmark is a spoke from the centre (easiest near the top, hardest opposite); a model reaches further out the better it scores, so each model is a polygon and the best-on-every-benchmark frontier is the outer hull. Every axis is normalised to its own 0–100%. Drag the time slider to watch the shape grow; hover a model to isolate it.

now

Normalised per benchmark (0–100% of each axis's own range). A model's polygon only touches the benchmarks it has a sourced score on. Hollow points are company-reported rather than independently confirmed. The full sourced-data matrix is in the table below; the same data is also on the line-chart view.

Every score, in full

The complete matrix behind the chart — 1084 sourced scores across 52 benchmarks (rows, oldest and most-saturated first) and 75 models (columns, by release date), so you can see exactly what we have and where the gaps are: 28% of possible cells are filled. Italic scores are company-reported rather than independently confirmed. Hover a score for the exact setting and provenance; click it to open the source. Scroll the table both ways.

Benchmark ↓   Model →GPT-4OpenAI · March 2023Claude 2Anthropic · July 2023Claude 3 OpusAnthropic · March 2024GPT-4oOpenAI · May 2024Claude 3.5 SonnetAnthropic · June 2024Llama 3.1 405BMeta AI · July 2024o1-previewOpenAI · September 2024o1OpenAI · December 2024o3OpenAI · December 2024DeepSeek-R1DeepSeek · January 2025Gemini 2.5 ProGoogle DeepMind · March 2025Qwen3 235BAlibaba / Qwen · April 2025Claude Opus 4Anthropic · May 2025Grok 4xAI · July 2025Kimi K2Moonshot AI · July 2025GPT-5OpenAI · August 2025Qwen3-MaxAlibaba / Qwen · September 2025Claude Sonnet 4.5Anthropic · September 2025GPT-5.1OpenAI · October 2025Gemini 3 ProGoogle DeepMind · November 2025Claude Opus 4.5Anthropic · November 2025GPT-5.2OpenAI · December 2025Gemini 3 FlashGoogle DeepMind · December 2025Claude Opus 4.6Anthropic · February 2026GLM-5Zhipu AI · February 2026Gemini 3 Deep Think v2Google DeepMind · February 2026Claude Sonnet 4.6Anthropic · February 2026Gemini 3.1 ProGoogle DeepMind · February 2026GPT-5.4OpenAI · March 2026Claude Mythos PreviewAnthropic · April 2026Claude Opus 4.7Anthropic · April 2026Kimi K2.6Moonshot AI · April 2026GPT-5.5OpenAI · April 2026DeepSeek V4DeepSeek · April 2026Gemini 3.5 FlashGoogle DeepMind · May 2026Claude Opus 4.8Anthropic · May 2026Claude Fable 5Anthropic · June 2026Claude Mythos 5Anthropic · June 2026GLM-5.2Zhipu AI · June 2026GPT-5.6 SolOpenAI · June 2026Claude Sonnet 5Anthropic · June 2026Grok 4.5xAI · July 2026GPT-5.6 TerraOpenAI · July 2026GPT-5.6 LunaOpenAI · July 2026Muse Spark 1.1Meta AI · July 2026Kimi K3Moonshot AI · July 2026Gemini 3.6 FlashGoogle DeepMind · July 2026Claude Opus 5Anthropic · July 2026Grok 4.6xAI · August 2026Gemini 3.7 FlashGoogle DeepMind · August 2026GLM-5.3Zhipu AI · August 2026Claude Fable 5.1Anthropic · September 2026Step 5 PreviewStepFun · September 2026Gemini 3.8 FlashGoogle DeepMind · September 2026GPT-6 AstraOpenAI · September 2026Grok 4.7xAI · September 2026GPT-6 SolOpenAI · September 2026Claude Opus 5.5Anthropic · September 2026GPT-6 LunaOpenAI · September 2026MiMo-V2.6-ProXiaomi · September 2026Claude Sonnet 5.5Anthropic · September 2026GPT-6.1 SolOpenAI · September 2026Gemini 4 ArgonGoogle DeepMind · September 2026BeamReflection AI · October 2026Mistral Large 4Mistral AI · October 2026Claude Haiku 5.5Anthropic · October 2026Muse Wonder FullMeta AI · October 2026Muse WonderMeta AI · October 2026Muse Spark OpenMeta AI · October 2026DeepSeek V4.1 Flash (1017)DeepSeek · October 2026MiniMax M3.1 FlashMiniMax · October 2026Kimi K3.1 ProMoonshot AI · October 2026GPT-6.1 TerraOpenAI · October 2026Gemini 4 CarbonGoogle DeepMind · October 2026Claude Fable 5.2Anthropic · November 2026n
GSM8Ksaturated92%95%96.4%96.8%92.12%92.6%6
ARC-AGI-2live89.2%92.5%52.6%83.9%59.5%60.4%60.4%90.4%67.1%84.6%90%89.2%95%61.4%89.6%93.3%59.3%83.9%94.2%91.3%23.5%61.3%57.5%78.1%93.75%25
MMLUsaturated86.4%86.8%88.7%90.4%88.6%91.8%90.8%89.5%90.1%9
AIMEcontaminated13.4%83%79.2%96.7%79.8%86.7%85.7%75.5%91.7%69.6%94.6%87%95%93%100%92.7%16
HumanEvalsaturated67%71.2%84.9%91%92%89%76.8%7
MATHsaturated42.2%60.1%76.6%71.1%73.8%94.8%97.3%98%97.4%64.5%10
MMLU-Prolive68.5%72.55%76.12%73.3%84%85.3%81.1%87.5%8
GPQAsaturating38.8%50.4%49.9%59.4%50.7%75.7%87.7%71.5%84%71.1%79.6%87.5%75.1%85.7%83.4%91.9%87%92.4%86%94.3%94.6%93.6%90.1%92%92.6%94.1%94.6%92.9%92.3%93.5%96%90.6%89%94.2%34
MMMUlive56.8%59.4%69.1%68.3%77.3%82.9%81.7%76.5%76.5%84.2%77.8%80.7%12
OSWorld-Verifiedsaturated14.9%61.4%66.3%76.2%75%78.7%83.4%85%85%84.8%83%82%80.4%13
LMArenadisputed1227 Elo1253 Elo1300 Elo1443 Elo1501 Elo1436 Elo1452 Elo1503 Elo1475 Elo1485 Elo1461 Elo1466 Elo1467 Elo1490 Elo1487 Elo1483 Elo1491 Elo1456 Elo1490 Elo1481 Elo1503 Elo1496 Elo1476 Elo1459 Elo1509 Elo1480 Elo1478 Elo1480 Elo1517 Elo1509 Elo30
SWE-benchsaturating33.2%49%48.9%71.7%49.2%63.8%72.5%65.8%74.9%69.6%77.2%76.2%80.9%80%77.8%80.6%80.6%88.6%96%81.6%20
GraphWalks 256k–1Mlive38.7%80%58.6%65%71.8%66.8%84.2%96.2%8
MindCubelive48.1%51.2%57.6%59.6%64.7%59.7%58.3%62%77.3%61.2%61.7%78.3%67%60%84.1%70.4%63.9%75.6%79.9%83.9%64.9%83.1%76.8%78.1%62.6%57.8%80.1%83.3%84.3%88.4%84.5%92.2%92.7%93.1%89.1%96.7%91.1%81.4%38
OSWorld-2.0 Aug (partial)live62.72%68.31%61.7%3
OSWorld-2.0 Aug offline (partial)live64.13%70.19%72.6%71.4%69.2%5
OSWorld-2.1 (partial)live57%77.67%80.7%81.8%80.1%78.4%72.6%79.6%8
ARC-AGI-1saturated9%21%82.8%15.8%24.3%66.7%65.7%63.7%80%86.2%98.5%97.5%87.2%96.5%88%94.5%91.2%97.5%87.5%95.5%97.5%98.5%98.5%90.2%95.5%98.5%92.5%96.5%98.5%98.5%79.1%90.1%94%94.5%98.5%35
GDPval-AA v1saturating1314 Elo1769 Elo1554 Elo1890 Elo1932 Elo1932 Elo6
SWE-bench Prolive11.18%21.41%27.67%41.78%43.6%43.3%45.89%29.94%34.63%51.9%46.1%59.1%77.8%58.6%55.4%69.2%80.3%80.3%62.1%64.6%63.2%64.7%63.4%62.7%61.5%58.7%79.2%89.9%81.3%66.1%64.8%93%32
MathVistasaturating49.9%50.5%63.8%67.7%71%86.8%6
ERQAlive47%53.3%60.5%60.8%50.1%58.8%50.3%59.8%70.2%54%60.7%71%54.8%56.6%74.2%64.8%58.1%61.3%70.5%75.4%59.5%67.8%71.2%63.6%63.6%62.4%66.5%66.1%70.8%77.7%70.3%79.6%82.3%75.1%78.2%86.5%75.3%66.2%38
DeepSWElive29.9%11.7%51.8%67%36.1%59%69.9%46.2%72.7%53.8%53.8%69.6%67.2%53.3%68.5%46.7%73.6%67.5%65.5%69%67.7%73.8%74.1%71%68.8%74.2%66.6%71.9%71%75.2%77.9%43.3%61.7%79%78.8%60%77%73.7%75.5%74.3%40
CWE-bench v1live57%58%68%68%52%67%68%71%8
SpatialVizlive31.1%41.4%47.7%46.6%34.8%54.1%41.6%51.3%63.2%43%65.8%65.3%55.7%54.9%66.1%69.3%62.6%73.9%74.2%73.9%65.2%73.9%80.7%61.1%65.2%71.3%70.3%71.2%75.8%75.3%77.9%78.1%93.1%89.7%90.3%94.2%83.5%69.8%38
ExploitBenchlive25.8%26.1%77.7%27.7%18.4%47.4%40%78%73.5%31%52.9%33.2%70%100%47.9%80%99.7%87%49%58.9%74.7%21
IntPhys 2live53%53.1%54.7%56%54.9%56.1%54.4%52%56.9%56.3%58.3%63.4%53.6%50.8%53.6%56.4%56%60%59.9%67%55.1%67.1%63.9%61.4%61.3%58%66.8%58.6%65.1%68.2%67.7%62.5%77.4%68.3%72.3%74.6%70.2%64.9%38
Vals Index v2.2live52.95%59.73%55.95%65.02%58.56%70.18%52.32%57.81%70.85%63.94%69.24%43.42%58.73%66.79%64.88%48.57%61.26%53.78%62.52%60.54%70.36%71.31%22
HealthBenchlive43.8%51.8%56.9%60.9%66%60.5%57.8%57.7%55.7%59.8%48.5%63.4%56.7%65.6%69.2%64.2%56.5%64.8%62.3%60.5%68.1%21
Riemann-benchlive11.2%37.6%27.2%33.6%41.6%32.8%7.2%55.2%38.4%36.8%47.2%60%10.4%74.4%38.4%66.4%20.8%37.6%30.4%68%39.2%12%65.6%51.2%72%64.8%69.6%59.2%76%24%80%31
FrontierSWE 2live47%32.2%25.9%52%25.3%20.3%30.2%56.3%19.6%65.5%29.5%62.3%61.9%55%43.8%61.2%69.94%17
GDPval-AA v2.1live1233 Elo1247 Elo1353 Elo1351 Elo1202 Elo1454 Elo1610 Elo1609 Elo1464 Elo1452 Elo1460 Elo1211 Elo1534 Elo1286 Elo1722 Elo1647 Elo1396 Elo1649 Elo1755 Elo1587 Elo1436 Elo1574 Elo1714 Elo1509 Elo1866 Elo1433 Elo1683 Elo1838 Elo1596 Elo1624 Elo1177 Elo1422 Elo1619 Elo1857 Elo1770 Elo1401 Elo1746 Elo1458 Elo1846 Elo1476 Elo1733 Elo1831.33 Elo42
AA Intelligence Index v5.0live31.74928.530.556.934.358.427.829.954.254.550.417.725.336.249.743.324.732.528.9465159.464.5624
Codeforces / CodeContestslive392 Elo808 Elo1673 Elo2727 Elo2029 Elo2056 Elo3455 Elo3206 Elo8
HLE-Verifiedlive54.5%31%51.1%54.4%53.6%54.9%6
HLE-Diamondlive3%6.6%4.4%8.1%11.1%7.1%4.5%6.3%20.2%5.5%10.1%18.2%13.4%7.3%31.8%21.1%20.4%12.4%27.9%9.4%25.7%23.1%45.6%30.4%18.4%15.9%15.6%31.3%21.8%38.1%19.6%31.2%22.7%51.6%33.3%59.9%22.8%54.6%53.2%56.9%34.7%74.3%42
ARC-AGI-3live0.5%0.4%0.2%0.2%0.4%1.5%7.8%0.3%0.8%0.2%30.2%2.1%10.4%62.7%1.8%4.6%0.2%24.3%52.7%49.8%0.5%81.17%22
ARC-AGI-3 (Provider Adapter)saturating35%99.9%10%23%0.6%72.4%96.4%97.5%2.8%97.72%10
OSWorld-2.0 Auglive27.34%31.43%2
OSWorld-2.1live25.6%44.33%42.8%48.7%43.5%39.4%34.3%7
Terminal-Bench Science 0.1live10.5%21.4%22.4%8.6%3.3%7.1%30%7.1%5.7%8.1%40%12.4%68.1%14.3%63.3%59.9%57%57.6%38.1%58.3%64.8%74.6%22
TextQuestslive13.1%30.9%15.2%23.2%27.8%30%31%34.2%41%38.7%37%36.4%40.8%31.5%45.8%42.2%37%27.4%48.9%20.3%35.7%40.1%56.1%52.1%25.4%40.5%30.8%24.9%40%53.3%47.3%52.9%32%56.6%54.1%74.2%57.3%71.4%77.3%47.6%27.8%41
Terminal-Bench 4.0live23.6%44.5%37.3%12.4%12.4%21.5%17.3%53.9%20.3%11.2%41.8%57.9%33.3%19.1%58.2%37.6%49.4%64.8%16.4%34.9%61.8%58.2%57.4%28.3%39.2%57.1%52%42.3%38.1%65.7%50.3%65.2%67.6%33
HLE (no tools)live2.7%4.3%9.1%20.3%8.5%18.8%10.7%25.4%4.7%24.8%7.65%27.2%37.5%30.8%34.5%36.6%34.2%48.4%21.1%44.4%40.3%39%35.5%41.4%37.7%42.5%49.8%52.7%59%45.5%39.3%35.9%31.8%49.4%43.5%51%39.7%45.6%39.1%60.9%46.2%53.6%64.4%56.9%51.3%55.6%45.9%47.6%44.8%42.6%51.1%66.28%52
Chartographylive26.1%29.6%16.5%12.2%31%15.9%34.8%45%16.6%17%34%31.4%24.4%26.6%34%27.3%20.5%40.4%46.2%40.9%71%14.7%53.6%66.3%29.1%61.6%71.6%46.4%11.6%72.5%73.4%31
Blueprint-Bench 2live6.7%26.5%27.1%24.5%3.9%36.2%33.6%14.5%38.6%33.6%24.9%27.3%30.8%22.6%29.5%31.2%30.4%33.2%41.9%38.6%49.7%32.5%36.9%51.2%31.2%39.3%54.4%33%42.1%58.6%56.6%31
Terminal-Bench 3.0live34.1%34.6%15.7%26%28.3%5
Agents' Last Exam v1.0retired16.4%20.5%21.1%9.2%26.6%12.4%27%25.7%20.4%30.6%27%28%30.3%28.3%32.2%34.2%32.2%38.2%18
Agents' Last Exam v1.1live30.3%5.7%35.2%26.2%39.3%42.6%37.7%29.5%41.8%9
AutomationBenchlive5.33%8.68%11.57%13.39%2.59%16.59%13.39%16.89%17.05%17.4%28.77%10.65%23.59%17.05%22.68%17.05%26.94%30.44%22.37%29.68%41.4%33.2%42.47%44.75%36.1%51.29%53.88%51.45%28
EnigmaEvallive0.8%5.7%11.9%5.6%7.8%10.5%6%11.7%17.8%12.4%14.5%18.3%7.6%9.1%32.4%27.6%15.6%5.5%37.2%23%20.5%41.3%39.2%17%23.1%19.1%16.6%23.6%43.9%33.9%44.2%37.2%69.7%57.8%59.5%64.6%36.1%14.7%38
SWE-sweeplive4.7%1.5%2.5%0.6%1.3%2.9%9.5%3.6%8
covered91919127115151114551391411581316159124213221841714221513252785331320272514251133172014254253316143112821233094159171510710712181084