UnifyBench

RankingMiniMax-M3

MiniMax-M3

Compare models

Data updated 22 Oct 2026

38 published benchmark measures · 10 benchmark families contribute across 4 task areas. 3 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Model evidence summary

This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →

Performance profile

Capabilities

Adjusted comparison score · 0–100
MiniMax-M3 capability radarComparison scores from 0 to 100. Unknown capabilities have no point; lines stop at gaps. Hollow points are preliminary. Exact values and support labels follow the chart.AgenticHard reasoningCodingHuman prefKnowledgeMultimodalLong context50100MiniMax-M3 · Agentic: 23.7 · SupportedMiniMax-M3 · Coding: 26.3 · SupportedMiniMax-M3 · Multimodal: 6.9 · Preliminary

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic6 families · 1 with independent evidence · Supported23.7

6 core families; 47 direct opponents across 17 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 17.7–28.5; 0/13 scenarios unsupported. Without one publisher: 20.5–27.6; 1/15 unsupported. Smoothing check: 20.5–30.5; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

  • GDPval: 64.3 observed win share
    MiniMax, artificialanalysis.ai · Source 1 Source 2
  • Browsecomp: 71.4 observed win share
    MiniMax · Source 1
  • Apex Agents: 40.0 observed win share
    MiniMax · Source 1
  • OSWorld: 40.0 observed win share
    MiniMax · Source 1
  • OfficeQA: 66.7 observed win share
    MiniMax · Source 1
  • MCP-Atlas: 71.4 observed win share
    MiniMax · Source 1
Hard reasoningNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 16/16 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    Coding2 families · 0 with independent evidence · Supported26.3

    2 core families; 7 direct opponents across 6 labs.

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: 22.8–37.3; 2/6 scenarios unsupported. Without one publisher: 24.1–36.1; 1/19 unsupported. Smoothing check: 26.0–30.1; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    • SWE-bench Pro: 83.3 observed win share
      MiniMax · Source 1
    • SWE-bench Verified: 50.0 observed win share
      MiniMax · Source 1
    Human pref1 families · 1 with independent evidence · PreliminaryUnknown

    1 core families; 76 direct opponents across 17 labs. No connected comparison to the complete reference panel

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    • Human preference (Arena): 64.5 observed win share
      lmarena.ai · Source 1
    KnowledgeNo comparable evidenceUnknown

    0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      Multimodal1 families · 0 with independent evidence · Preliminary6.9

      1 core families; 5 direct opponents across 4 labs. Needs broader benchmark and opponent support

      Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

      Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

      Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

      Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      • Mmmu Pro: 40.0 observed win share
        MiniMax · Source 1
      Long contextNo comparable evidenceUnknown

      0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

      Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

      Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

      Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

      Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

        Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.

        Reported effort · Not specified

        Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.

        Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.

        Inspect each result and its source ↓ · Download effort evidence
        Score contributions and missing evidence

        10 contributing families across 4 capabilities. Fixed reference panels do not change when the catalog expands.

        Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.

        Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.

        Model information & shareable badge
        Lab
        MiniMax
        Catalog status
        active
        Availability
        Documented provider API; downloadable official weights
        Family
        MiniMax
        Released
        —
        Context
        1,000,000 tokens
        License
        —
        Model card
        https://platform.minimax.io/docs/api-reference/text-anthropic-api
        Default Capability family coverage
        Documented-evidence family coverage/badge/minimax-m3.svg
        Benchmark scores & sources

        Original results, evaluation harnesses, and evidence behind this model.

        BenchmarkBucketScoreHarnessEvidenceSource-recorded date
        APEX-Agents · source release snapshot; version not specifiedAgentic27.7%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        contributes to capability        		lab self-reportReviewed 2026-09-06
        Artificial Analysis Cyber IndexSupporting evidence22.3880159084502 Artificial Analysis Stirrup · Cyber Index v1.0 · unspecified

        Effort: Unspecified

        Cyber Index source settings

        Artificial Analysis Stirrup, v1.0. Display only. This composite measures defensive source-code tasks. Successful capability scores depend on safety refusals, and refusal rates are reported separately. It does not enter weighted Overall.

        Official Cyber Index board
        		official board

        Supporting evidence outside the reviewed capability core

        		2026-10-21
        AutomationBench-AASupporting evidence21.25125760074941%Artificial Analysis AutomationBench-AA

        Effort: Not specified

        		official board

        Supporting evidence outside the reviewed capability core

        		2026-10-20
        BankerToolBench · source release snapshot; version not specifiedSupporting evidence76.1%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        BrowseComp · source release snapshot; version not specifiedAgentic83.5%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        contributes to capability        		lab self-reportReviewed 2026-09-06
        CL-bench · source release snapshot; version not specifiedSupporting evidence20.5%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        Claw-Eval · source release snapshot; version not specifiedSupporting evidence74.5%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        DRACO · source release snapshot; version not specifiedSupporting evidence73.2%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        GDPval rubrics · source release snapshot; version not specifiedAgentic74.8%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        contributes to capability        		lab self-reportReviewed 2026-09-06
        GDPval-AAAgentic1242Artificial Analysis GDPval-AA

        Effort: Not specified

        contributes to capability        		official board2026-10-22
        GPQA DiamondHard reasoning92.929%GPQA Diamond reported

        Effort: Not specified

        		independent repro

        No matched opponent in this evaluation unit

        		2026-10-16
        IMO 2025 · source release snapshot; version not specifiedSupporting evidence35 points / 42
        Reported settings & source

        MiniMax points out of42; comparator percentages as printed

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        KernelBench Hard · source release snapshot; version not specifiedSupporting evidence28.8%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        LiveSQLBench · source release snapshot; version not specifiedSupporting evidence40.2%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        LMArena Agent ArenaSupporting evidence-9.63 LMArena Agent Arena · unspecified

        Effort: Not specified

        		official board

        Supporting evidence outside the reviewed capability core

        		2026-10-20
        LMArena Text ArenaHuman pref1441LMArena Text

        Effort: Not specified

        contributes to capability        		official board2026-10-20
        LOCA-Bench 256k · source release snapshot; version not specifiedSupporting evidence49.3%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        MCPAtlas · source release snapshot; version not specifiedAgentic74.2%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        contributes to capability        		lab self-reportReviewed 2026-09-06
        MMMU-Pro · source release snapshot; version not specifiedMultimodal78.1%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        contributes to capability        		lab self-reportReviewed 2026-09-06
        NL2Repo · source release snapshot; version not specifiedSupporting evidence42.1%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        OfficeQA Pro · source release snapshot; version not specifiedAgentic45.1%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        contributes to capability        		lab self-reportReviewed 2026-09-06
        OmniDocBench · source release snapshot; version not specifiedSupporting evidence91.6%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        OSWorld Verified · source release snapshot; version not specifiedAgentic75.2%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        contributes to capability        		lab self-reportReviewed 2026-09-06
        PaperBench · source release snapshot; version not specifiedSupporting evidence52.6%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06
        PostTrainBench · source release snapshot; version not specifiedSupporting evidence37.1%
        Reported settings & source

        MiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted.

        First-party reported result; comparator results retain the source evaluation setup.

        MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06

        		Published configuration

        Effort: Not specified

        		lab self-report

        Supporting evidence outside the reviewed capability core

        		Reviewed 2026-09-06